Triple

T3662729
Position Surface form Disambiguated ID Type / Status
Subject Battle of Marathon E77687 entity
Predicate location P40 FINISHED
Object Attica E7089 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: Attica | Statement: [Battle of Marathon, location, Attica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Attica
Context triple: [Battle of Marathon, location, Attica]
  • A. Attica chosen
    Attica is a historical region of central Greece that includes the capital city of Athens and has been a core center of Greek civilization since antiquity.
  • B. Blackwell's Island
    Blackwell's Island, now known as Roosevelt Island, is a narrow island in New York City's East River historically associated with hospitals, asylums, and prisons.
  • C. Fulton
    Fulton is a small city in northwestern Illinois known for its location along the Mississippi River and its Dutch heritage, including a working Dutch windmill.
  • D. Dannemora
    Dannemora is a residential suburb in East Auckland, New Zealand, known for its modern housing developments and family-oriented community.
  • E. Lincoln Prison
    Lincoln Prison is a correctional facility located in the city of Lincoln in Lincolnshire, England.
  • 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_69ad85dfc4dc8190a441864202ab2a7a completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc3fcd910819082012b10b23860aa completed March 8, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b48846af9881909d71d63b8bd8d141 completed March 13, 2026, 9:57 p.m.
Created at: March 8, 2026, 3:25 p.m.