Triple

T11433126
Position Surface form Disambiguated ID Type / Status
Subject The Bar-Kays E270935 entity
Predicate notableSingle P3283 FINISHED
Object Son of Shaft E925970 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: Son of Shaft | Statement: [The Bar-Kays, notableSingle, Son of Shaft]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Son of Shaft
Context triple: [The Bar-Kays, notableSingle, Son of Shaft]
  • A. Son of Shaft chosen
    "Son of Shaft" is a 1972 funk and soul track by The Bar-Kays, known for its driving groove and for building on the legacy of Isaac Hayes’ iconic "Theme from Shaft."
  • B. Son of a Gun
    Son of a Gun is a 2014 Australian crime thriller film following a young inmate who becomes entangled in a high-stakes heist under the mentorship of a notorious criminal.
  • C. John Shaft II
    John Shaft II is the tough, streetwise New York City detective and nephew of the original John Shaft, serving as the modern protagonist in the Shaft film franchise.
  • D. Hard Target
    Hard Target is a 1993 American action film directed by John Woo and starring Jean-Claude Van Damme, known for its stylized violence and Woo’s Hollywood debut.
  • E. von Shaft
    von Shaft is the surname of Broomhilda von Shaft, a fictional character from Quentin Tarantino’s film "Django Unchained."
  • 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d806c30d788190b0c939b33de89277 completed April 9, 2026, 8:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e8e371948190a37609aad75a4bfd completed April 20, 2026, 8:50 a.m.
Created at: April 8, 2026, 9:35 p.m.