src/knowledge_extraction/config/labels.yaml

# GLiNER entity labels. E1 tunes these WITHOUT touching code.
# Two variants so E1 can A/B label phrasing (GLiNER is sensitive to label wording).

default:
  - mining production metric
  - equipment availability term
  - operational abbreviation
  - machine or equipment type
  - time category
  - production activity
  - measurement unit

# Variant B: Indonesian-language label phrasing. GLiNER multi is multilingual;
# whether ID label strings improve ID recall is exactly what E1 tests.
id_phrasing:
  - istilah produksi tambang
  - parameter ketersediaan alat
  - singkatan operasional
  - jenis alat berat
  - kategori waktu kerja
  - aktivitas produksi
  - satuan pengukuran

# Variant C: the first two variants both missed the same class of terms —
# mining activities and materials (coal mining, land clearing, waste removal,
# joint survey). This variant adds labels for that class specifically.
broad:
  - mining production metric
  - equipment availability term
  - operational abbreviation
  - machine or equipment type
  - time category
  - mining activity
  - material or commodity
  - measurement unit
  - data source or system
  - work category
  - analysis method

# 0.25, not 0.35: the E1 sweep measured recall 0.854 @ 0.25 vs 0.658 @ 0.35 on the
# `broad` variant. Precision falls (0.41 vs 0.50) but the term filter is meant to be
# over-inclusive — clustering and evidence ranking absorb the noise, and a term the
# filter never proposes can never be recovered downstream.
threshold: 0.25