Triple

T5951497
Position Surface form Disambiguated ID Type / Status
Subject Roger Conant E132407 entity
Predicate familyName P18 FINISHED
Object Conant E51066 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: Conant | Statement: [Roger Conant, familyName, Conant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conant
Context triple: [Roger Conant, familyName, Conant]
  • A. Conant chosen
    Conant is a surname most notably associated with James B. Conant, an influential American chemist, educator, and former president of Harvard University.
  • B. Kogod
    Kogod is the business school of American University in Washington, D.C., offering undergraduate and graduate programs in business and management.
  • C. Metcalf
    Metcalf is an English-language surname of Anglo-Saxon origin, historically associated with northern England.
  • D. Shattuck
    Shattuck is a small town in northwestern Oklahoma known for its historic windmill park and rural, agricultural character.
  • E. Manton
    Manton is a neighborhood and village area located within Providence County in the state of Rhode Island.
  • 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_69c0086b05cc8190a8f36a96927a525c completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03981d88c8190838998494ad50a19 completed March 22, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3d1801c819093dc43dc5a525796 completed March 23, 2026, 6:55 a.m.
Created at: March 22, 2026, 4:02 p.m.