Triple

T6709784
Position Surface form Disambiguated ID Type / Status
Subject Wiltshire E153106 entity
Predicate contains P35 FINISHED
Object Old Sarum E85295 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: Old Sarum | Statement: [Wiltshire, contains, Old Sarum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Sarum
Context triple: [Wiltshire, contains, Old Sarum]
  • A. Old Sarum chosen
    Old Sarum was a notorious English "rotten borough" parliamentary constituency with virtually no residents, long used to control seats in the House of Commons before electoral reform.
  • B. Berkhamsted Castle
    Berkhamsted Castle is a medieval motte-and-bailey fortress in Hertfordshire, England, historically significant as a royal stronghold and residence of notable figures including Richard, 1st Earl of Cornwall.
  • C. Uffington Castle
    Uffington Castle is an Iron Age hillfort in Oxfordshire, England, known for its impressive earthworks and proximity to the prehistoric Uffington White Horse.
  • D. Marlborough Castle
    Marlborough Castle was a medieval royal stronghold in Wiltshire, England, that served as a residence for English monarchs and their consorts.
  • E. Tilbury Fort
    Tilbury Fort is a historic artillery fort on the north bank of the River Thames in Essex, England, best known for defending London from seaborne attack from the 16th century onwards.
  • 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_69c68808d8d8819087369015270788fe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d105b49c8190932246a727e2c513 completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c700906a9c81908a121db4291195d8 completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:06 p.m.