Triple

T12201995
Position Surface form Disambiguated ID Type / Status
Subject Gangster and a Gentleman E290737 entity
Predicate hasPart P35 FINISHED
Object I Know E604003 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: I Know | Statement: [Gangster and a Gentleman, hasPart, I Know]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: I Know
Context triple: [Gangster and a Gentleman, hasPart, I Know]
  • A. I Know chosen
    "I Know" is a song featured on the album "Confrontation."
  • B. I Know
    "I Know" is a song by Big Sean featuring Jhené Aiko from his 2015 studio album Dark Sky Paradise.
  • C. I Know, You Know
    "I Know, You Know" is the upbeat, ska-influenced theme song performed by The Friendly Indians for the television series Psych.
  • D. You Know
    "You Know" is a song by English singer-songwriter Laura Marling from her 2013 album *Once I Was an Eagle*, noted for its intimate folk style and introspective lyrics.
  • E. I Know What I Know
    "I Know What I Know" is a song by Paul Simon, featured on his acclaimed 1986 album *Graceland* and noted for its incorporation of South African musical influences.
  • 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c7b97408190a11ea37cc6edf18c completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a982e308190979245ac9643465a completed May 2, 2026, 2:30 p.m.
Created at: April 8, 2026, 9:51 p.m.