Triple

T18220986
Position Surface form Disambiguated ID Type / Status
Subject Captain Stillman E436302 entity
Predicate hasFullName P16 FINISHED
Object Captain 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: Captain Stillman | Statement: [Captain Stillman, hasFullName, Captain Stillman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Captain Stillman
Context triple: [Captain Stillman, hasFullName, Captain Stillman]
  • A. Captain Stillman chosen
    Captain Stillman is a bumbling, self-important U.S. Army officer portrayed by John Larroquette in the comedy film "Stripes."
  • B. Captain Brice
    Captain Brice is a minor character in Tom Stoppard’s play "Arcadia," serving as a military officer connected to the aristocratic household around which the drama’s events unfold.
  • C. Captain Riga
    Captain Riga is a fictional sea captain who appears as a character in Herman Melville’s novel "Redburn: His First Voyage."
  • D. Captain Killy
    Captain Killy is the ruthless Mirror Universe counterpart of Sylvia Tilly in the Star Trek: Discovery series.
  • E. Captain Farver
    Captain Farver is the airline pilot protagonist in the Twilight Zone episode "The Odyssey of Flight 33," who struggles to lead his crew and passengers after their jet mysteriously slips through time.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47b5bfc819085c5935c08361ba9 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.