Triple

T18886165
Position Surface form Disambiguated ID Type / Status
Subject Barbara De Fina E461960 entity
Predicate workedOn P3 FINISHED
Object Mad Dog and Glory E743312 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: Mad Dog and Glory | Statement: [Barbara De Fina, workedOn, Mad Dog and Glory]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mad Dog and Glory
Context triple: [Barbara De Fina, workedOn, Mad Dog and Glory]
  • A. Mad Dog and Glory chosen
    Mad Dog and Glory is a 1993 dark comedy-crime film starring Robert De Niro, Uma Thurman, and Bill Murray, blending offbeat humor with a quirky romantic storyline.
  • B. Mad Dogs
    Mad Dogs is a British dark comedy-drama television series about a group of middle-aged friends whose holiday in Spain spirals into crime and chaos.
  • C. Mad Dog
    Mad Dog is the vicious outlaw gunslinger and primary antagonist in the 1885 segment of the film "Back to the Future Part III."
  • D. Road Dog
    "Road Dog" is a song by the rock band Natural History.
  • E. Three Dog
    Three Dog is the charismatic, freedom-fighting DJ of Galaxy News Radio in Fallout 3, known for his distinctive voice, moral commentary, and guidance to the Lone Wanderer.
  • 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_69d8dcfc3430819095ee6fc0eb4c06a5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c4760d808190b502c4ed1f24424c completed April 20, 2026, 6:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0591090fd48190aa3bf37fd26f659d completed May 14, 2026, 9:08 a.m.
Created at: April 10, 2026, 11:57 a.m.