Triple

T1903321
Position Surface form Disambiguated ID Type / Status
Subject André Broca E37741 entity
Predicate familyName P18 FINISHED
Object Broca E37741 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: Broca | Statement: [André Broca, familyName, Broca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Broca
Context triple: [André Broca, familyName, Broca]
  • A. Broca chosen
    Broca is a French surname most famously associated with Paul Broca, the 19th-century physician and anatomist who identified the brain region responsible for speech production.
  • B. Broca's area
    Broca's area is a region in the frontal lobe of the dominant hemisphere of the brain that is crucial for speech production and language processing.
  • C. Neurath
    Neurath is a surname most prominently associated with Otto Neurath, an Austrian philosopher of science and key member of the Vienna Circle.
  • D. Wernicke area
    Wernicke area is a region of the human brain’s temporal lobe crucial for understanding spoken and written language.
  • E. Badiot
    Badiot is a regional variety of the Ladin language spoken in parts of the Dolomite region of northern Italy.
  • 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb1909aec8190b3259c8f969ce81e completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3d0d01c8190ae0c8029fead4008 completed March 8, 2026, 10:10 p.m.
Created at: March 4, 2026, 7:35 p.m.