Triple

T18404823
Position Surface form Disambiguated ID Type / Status
Subject Thomas Weld E450096 entity
Predicate familyName P18 FINISHED
Object Weld NE NERFINISHED

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: Weld | Statement: [Thomas Weld, familyName, Weld]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Weld
Context triple: [Thomas Weld, familyName, Weld]
  • A. Weld chosen
    Weld is a surname of English origin borne by various notable individuals, including American abolitionist Theodore Dwight Weld.
  • B. Weld
    Weld is a live album by Neil Young and Crazy Horse, renowned for its intense, feedback-heavy performances of his rock classics.
  • C. Weld
    Weld is a farming simulation game in the Harvest Moon series that precedes the installment titled Harvest Moon.
  • D. Weld
    Weld is an American actress known for her work in film and television from the 1950s through the 1990s, including acclaimed performances in movies like "Play It As It Lays" and "Looking for Mr. Goodbar."
  • E. Bessemer
    Bessemer is an industrial city in Jefferson County, Alabama, historically known for its steelmaking and manufacturing.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e51956b8c88190b863e66871825014 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.