Triple

T22275853
Position Surface form Disambiguated ID Type / Status
Subject William James Stillman E550603 entity
Predicate familyName P18 FINISHED
Object Stillman 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: Stillman | Statement: [William James Stillman, familyName, Stillman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stillman
Context triple: [William James Stillman, familyName, Stillman]
  • A. Doak
    Doak is a masculine given name most famously associated with American football star and Heisman Trophy winner Doak Walker.
  • B. McClymonds
    McClymonds is a public high school in West Oakland, California, known for its strong athletic tradition and deep roots in the local community.
  • C. Isaiah Stillman chosen
    Isaiah Stillman was a militia officer best known for leading U.S. forces in the 1832 Battle of Stillman’s Run during the Black Hawk War.
  • D. Toomer
    Toomer is a party involved in the U.S. Supreme Court case Toomer v. Witsell, which addressed constitutional limits on state discrimination against nonresident commercial fishers.
  • E. LeRoy
    LeRoy is the middle name of American political consultant and Republican strategist Lee Atwater.
  • 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_69e11e43d8208190aff4f9cf7f2c2a8a completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea7ebbc8190948e8994e988adb3 completed April 29, 2026, 12:19 a.m.
Created at: April 16, 2026, 8:40 p.m.