Triple

T14747438
Position Surface form Disambiguated ID Type / Status
Subject Hunter line E346508 entity
Predicate connectsTown P845 FINISHED
Object Scone E86021 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: Scone | Statement: [Hunter line, connectsTown, Scone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scone
Context triple: [Hunter line, connectsTown, Scone]
  • A. Scone
    Scone is a historic Scottish village best known as the traditional coronation site of Scottish kings and the location of the Stone of Scone.
  • B. Scone chosen
    Scone is a rural town in New South Wales, Australia, known as the "Horse Capital of Australia" for its prominent thoroughbred breeding industry.
  • C. Haggis
    Haggis is a traditional Scottish savory pudding made from sheep offal, oatmeal, and spices, typically encased in a sheep’s stomach.
  • D. Eccles cake
    Eccles cake is a traditional British pastry made of flaky, buttery pastry filled with spiced currants and often enjoyed as a sweet snack or dessert.
  • E. Ribwich
    Ribwich is a fictional limited-time pork sandwich from The Simpsons’ Krusty Burger, parodying fast-food promotional items like McDonald’s McRib.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7d116e88190828b163b18d80f68 completed April 14, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0ce843a481908f376172d4a8b70a completed May 8, 2026, 4:18 p.m.
Created at: April 10, 2026, 1:30 a.m.