Triple

T20012308
Position Surface form Disambiguated ID Type / Status
Subject Tom Snout E494617 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Robin Starveling NE NERFINISHED

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: Robin Starveling | Statement: [Tom Snout, associatedWithCharacter, Robin Starveling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robin Starveling
Context triple: [Tom Snout, associatedWithCharacter, Robin Starveling]
  • A. Robin Starveling chosen
    Robin Starveling is a minor comic character in Shakespeare’s *A Midsummer Night’s Dream*, a tailor who plays the role of Moonshine in the craftsmen’s play-within-the-play.
  • B. Erispoe
    Erispoe was a 9th-century Breton ruler who consolidated Brittany’s independence from the Frankish kingdom and is often regarded as one of its early kings.
  • C. Jennet Humfrye
    Jennet Humfrye is the vengeful ghost central to Susan Hill’s gothic horror novel "The Woman in Black," haunting Eel Marsh House and the surrounding village.
  • D. Blifil
    Blifil is a hypocritical and scheming antagonist in Henry Fielding’s novel "The History of Tom Jones, a Foundling."
  • E. Robin Tallon
    Robin Tallon is a former Democratic U.S. Representative from South Carolina who served in Congress during the 1980s and early 1990s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623773d88190826616a02d3c3e69 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:34 p.m.