Triple

T10210318
Position Surface form Disambiguated ID Type / Status
Subject The Sieve and the Sand E242307 entity
Predicate relatedWork P37 FINISHED
Object Burning Bright E242308 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: Burning Bright | Statement: [The Sieve and the Sand, relatedWork, Burning Bright]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burning Bright
Context triple: [The Sieve and the Sand, relatedWork, Burning Bright]
  • A. "Burning Bright" chosen
    "Burning Bright" is the third and final section of Ray Bradbury's dystopian novel Fahrenheit 451, depicting the climax of Montag's rebellion against his oppressive, book-burning society.
  • B. Beside the Dying Fire
    "Beside the Dying Fire" is the season two finale episode of the television series The Walking Dead, notable for introducing the iconic character Michonne.
  • C. The Day on Fire
    The Day on Fire is a biographical novel by James Ramsey Ullman that dramatizes the turbulent life and adventures of French poet Arthur Rimbaud.
  • D. Fuel for the Flame
    Fuel for the Flame is a novel by British writer Alec Waugh, known for its exploration of personal relationships and social mores in mid-20th-century settings.
  • E. The Burning
    "The Burning" is a popular episode of the sitcom *Seinfeld*, best known for featuring George Costanza’s “jerk store” comeback and Kramer’s storyline about medical students observing operations.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d395fbed008190b66996f5bb397853 completed April 6, 2026, 11:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d652cca9c081909f705365c70db009 completed April 8, 2026, 1:06 p.m.
Created at: April 6, 2026, 11:01 a.m.