Triple

T11400158
Position Surface form Disambiguated ID Type / Status
Subject Casa de las Conchas E270085 entity
Predicate municipality P852 FINISHED
Object Salamanca E55297 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Salamanca | Statement: [Casa de las Conchas, municipality, Salamanca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salamanca
Context triple: [Casa de las Conchas, municipality, Salamanca]
  • A. Salamanca chosen
    Salamanca is a historic city in western Spain renowned for its ancient university, golden sandstone architecture, and well-preserved medieval old town.
  • B. Salamanca
    Salamanca is an industrial city in central Mexico known for its major oil refinery and role in the country's petrochemical sector.
  • C. Salamanca
    Salamanca is a Chilean town and municipality in the Coquimbo Region, known for its agricultural production and location in the Choapa Valley.
  • D. Alcalá de Henares
    Alcalá de Henares is a historic Spanish city east of Madrid, renowned as the birthplace of Miguel de Cervantes and for its well-preserved university and medieval architecture.
  • E. Alcalá la Real
    Alcalá la Real is a historic town in southern Spain known for its imposing La Mota fortress and strategic location between Granada and Jaén.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d6aacdbc6c8190af6dc3d5f5d22836 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d8001adc188190ae45227856156412 completed April 9, 2026, 7:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8250c288190b5bff70f7445b815 completed April 20, 2026, 5:22 a.m.
Created at: April 8, 2026, 9:34 p.m.