Triple

T17316706
Position Surface form Disambiguated ID Type / Status
Subject Harland Williams E420444 entity
Predicate performedIn P795 FINISHED
Object RocketMan E1260998 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: RocketMan | Statement: [Harland Williams, performedIn, RocketMan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RocketMan
Context triple: [Harland Williams, performedIn, RocketMan]
  • A. RocketMan
    RocketMan is a science fiction novel by Peter Abrams, best known for its imaginative exploration of space travel and its impact on human relationships.
  • B. RocketMan chosen
    RocketMan is a 1997 science-fiction comedy film starring Harland Williams as an eccentric computer programmer-turned-astronaut on a disastrous mission to Mars.
  • C. Rocket Man
    "Rocket Man" is a 1972 Elton John song, written with Bernie Taupin, that became one of his signature hits and a defining space-themed pop ballad of the era.
  • D. Rocket Man
    Rocket Man is the popular NASCAR nickname of American stock car racing driver Ryan Newman, known for his exceptional qualifying speed.
  • E. Rocket Man
    "Rocket Man" is a humorous song by the satirical comic-strip band Pearls Before Swine, known for its folk-psychedelic style and cult following in the late 1960s and early 1970s.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4399d2fcc81909916302f141e236b completed April 19, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a018c4603f88190a713bf8260329ac3 completed May 11, 2026, 7:59 a.m.
Created at: April 10, 2026, 5:43 a.m.