Triple

T5731903
Position Surface form Disambiguated ID Type / Status
Subject Danny Torrance E126402 entity
Predicate relative P37 FINISHED
Object Abra Stone E195230 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: Abra Stone | Statement: [Danny Torrance, relative, Abra Stone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abra Stone
Context triple: [Danny Torrance, relative, Abra Stone]
  • A. Abra Stone chosen
    Abra Stone is a powerful young psychic (a "shiner") who plays a central role in Stephen King’s horror novel "Doctor Sleep," the sequel to "The Shining."
  • B. Abra
    Abra is a landlocked province in the northern Philippines known for its mountainous terrain, indigenous cultures, and rich natural landscapes.
  • C. Abra de Ilog
    Abra de Ilog is a coastal municipality in Occidental Mindoro, Philippines, known as a gateway between Mindoro Island and mainland Luzon via ferry connections.
  • D. Pichu
    Pichu is a small, baby Electric-type Pokémon known as the pre-evolved form of Pikachu, often depicted as playful and inexperienced with its own electricity.
  • E. Flega
    Flega is the summit of Mount Smolikas, one of the highest and most prominent peaks in Greece.
  • 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_69c0083082288190b7478cead6b5430a completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02532fd308190a7434dd42a55e9ac completed March 22, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a906e008190bd2b9a3481733f14 completed March 22, 2026, 9:09 p.m.
Created at: March 22, 2026, 3:47 p.m.