Triple

T2918183
Position Surface form Disambiguated ID Type / Status
Subject Robert Byrd E78656 entity
Predicate familyName P18 FINISHED
Object Byrd E133607 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: Byrd | Statement: [Robert Byrd, familyName, Byrd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Byrd
Context triple: [Robert Byrd, familyName, Byrd]
  • A. Byrd chosen
    Byrd is a variant spelling of the word "bird," often used as a surname or stylistic form.
  • B. Wingo
    Wingo is a Colombian low-cost airline operating domestic and international flights across Latin America and the Caribbean.
  • C. Birdy
    "Birdy" is a 1984 psychological war drama film, directed by Alan Parker and starring Matthew Modine and Nicolas Cage, about the intense post-Vietnam friendship between two traumatized young men.
  • D. Bagley Wright
    Bagley Wright was an American real estate developer and arts patron best known for helping finance and develop major Seattle landmarks and cultural institutions.
  • E. George Swanson Starling
    George Swanson Starling was a key African American migrant whose life story in the early and mid-20th century exemplifies the struggles and aspirations of the Great Migration chronicled in Isabel Wilkerson’s work.
  • 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a41b4c81909d8ace8ab270ed3c completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0562c5b5081908026b3f590b03aca completed March 10, 2026, 5:34 p.m.
Created at: March 8, 2026, 2:54 p.m.