Triple

T15910070
Position Surface form Disambiguated ID Type / Status
Subject Criss Chros E385822 entity
Predicate hasFirstName P17 FINISHED
Object Criss E385822 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: Criss | Statement: [Criss Chros, hasFirstName, Criss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Criss
Context triple: [Criss Chros, hasFirstName, Criss]
  • A. Criss Chros chosen
    Criss Chros is a laid-back, good-natured slacker character from the TV series "30 Rock" who becomes Liz Lemon’s supportive long-term boyfriend and eventual husband.
  • B. Cris
    Cris is the first name of Cris Judd, an American choreographer, dancer, and actor known for his work in music videos and live performances.
  • C. Cris
    Cris is the first name of Cris Collinsworth, a former NFL wide receiver and prominent American football television broadcaster.
  • D. Crist
    Crist is a surname most prominently associated with American politician Charlie Crist, a former governor of Florida.
  • E. Kris
    Kris is an American daytime talk show hosted by Kris Jenner that briefly aired in 2013.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565ea7a8819097efffda366b5245 completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe6e844481908227ec9e46ac9f4d completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:52 a.m.