Triple

T23281262
Position Surface form Disambiguated ID Type / Status
Subject Wells Tower E588868 entity
Predicate givenName P17 FINISHED
Object Wells 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: Wells | Statement: [Wells Tower, givenName, Wells]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wells
Context triple: [Wells Tower, givenName, Wells]
  • A. Wells
    Wells is a small city in northeastern Nevada known as a historic railroad and travel junction near the intersection of Interstate 80 and U.S. Route 93.
  • B. Wells
    Wells is a historic cathedral city in Somerset, England, renowned for its medieval architecture and status as one of the smallest cities in the country.
  • C. Wells
    Wells is a small town in southwestern Vermont known for its rural character and proximity to Lake St. Catherine.
  • D. Wells chosen
    Wells is a common English surname borne by numerous notable individuals across literature, politics, science, and the arts.
  • E. Wells
    Wells is the former name of the community now known as Keene in Kern County, California.
  • 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_69e25d16e2c08190a291de254703129e completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19643b8908190a2c29552b272dc61 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 4:57 p.m.