Triple

T17125484
Position Surface form Disambiguated ID Type / Status
Subject Devon Sawa E415582 entity
Predicate notableWork P4 FINISHED
Object Casper E85509 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: Casper | Statement: [Devon Sawa, notableWork, Casper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Casper
Context triple: [Devon Sawa, notableWork, Casper]
  • A. Casper chosen
    Casper is a 1995 family fantasy film about a friendly ghost who befriends a young girl while haunting a crumbling mansion.
  • B. Casper, Wyoming
    Casper, Wyoming is a city in central Wyoming known historically as an oil boomtown and regional hub for energy, commerce, and outdoor recreation.
  • C. Casperia
    Casperia is a historic hilltop village in central Italy’s Lazio region, known for its medieval architecture and panoramic views over the Sabine countryside.
  • D. Garson
    Garson is a masculine given name most notably associated with American writer and director Garson Kanin.
  • E. Keystone City
    Keystone City is a fictional American city in DC Comics, best known as one of the primary home cities of the superhero The Flash.
  • 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f026ae188190b8c1e08529719878 completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a12a7288190911c1be2667916c0 completed May 11, 2026, 2:08 a.m.
Created at: April 10, 2026, 5:36 a.m.