Triple

T16151077
Position Surface form Disambiguated ID Type / Status
Subject James Killian E391909 entity
Predicate familyName P18 FINISHED
Object Killian E33895 NE FINISHED

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: Killian | Statement: [James Killian, familyName, Killian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killian
Context triple: [James Killian, familyName, Killian]
  • A. Killian chosen
    Killian is a surname most notably associated with James R. Killian Jr., an influential American engineer and former president of the Massachusetts Institute of Technology.
  • B. Killian Overmeire
    Killian Overmeire is a Belgian former professional footballer best known as a long-serving midfielder and key figure for K.S.C. Lokeren.
  • C. Kayl
    Kayl is a commune in southwestern Luxembourg known for its industrial heritage and proximity to the country’s steel-producing region.
  • D. Aiden Burn
    Aiden Burn is a fictional crime scene investigator and key member of the forensic team on the television series CSI: NY.
  • E. Killam
    Killam is a surname most notably associated with Canadian financier and philanthropist Izaak Walton Killam, whose legacy includes major educational and research funding.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d981950819087fdacc7879dca97 completed April 17, 2026, 11:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7a9ebf08190aa21cdff051f4ba2 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:01 a.m.