Triple

T27461419
Position Surface form Disambiguated ID Type / Status
Subject Lt. Col. Kirby Yorke E692754 entity
Predicate similarCharacterTo P94757 FINISHED
Object Captain Kirby York from Fort Apache 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 Kirby York from Fort Apache | Statement: [Lt. Col. Kirby Yorke, similarCharacterTo, Captain Kirby York from Fort Apache]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: similarCharacterTo
Context triple: [Lt. Col. Kirby Yorke, similarCharacterTo, Captain Kirby York from Fort Apache]
  • A. namedForSimilarityTo
    Indicates that one entity is given its name because of a perceived resemblance or likeness to another entity.
  • B. moreSimilarTo
    Indicates that one entity bears a greater degree of similarity to a second entity than to a third entity, according to some defined similarity measure.
  • C. lessSimilarTo
    Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
  • D. hasSimilarityTo chosen
    Indicates that one entity shares common characteristics, features, or qualities with another entity to a notable degree.
  • E. characterCorrespondsTo
    Indicates that one character is equivalent to, maps onto, or represents another character in a defined correspondence or mapping.
  • F. None of above.

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_69ef5207903881909427745cda05d27a completed April 27, 2026, 12:09 p.m.
NER Named-entity recognition batch_69f62dfa4f3881908a45c137df7fa0db completed May 2, 2026, 5:01 p.m.
PD Predicate disambiguation batch_69f623aaf40081909f947431424a1d55 completed May 2, 2026, 4:17 p.m.
Created at: April 27, 2026, 12:50 p.m.