Triple

T8584478
Position Surface form Disambiguated ID Type / Status
Subject Oakington E203268 entity
Predicate hasRoadAccessTo P22549 FINISHED
Object A14 E216803 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: A14 | Statement: [Oakington, hasRoadAccessTo, A14]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A14
Context triple: [Oakington, hasRoadAccessTo, A14]
  • A. A14 chosen
    A14 is a major trunk road in England that forms a key east–west freight and commuter route linking the Midlands to the East Coast ports.
  • B. A12
    The A12 is a major road in England that connects London with East Anglia, serving key towns and cities including Ipswich and Colchester.
  • C. A12
    A12 is a major Swiss motorway that connects the regions of Bern and Fribourg, serving as an important north–south transit corridor.
  • D. A13
    A13 is a major Swiss motorway running along the country’s eastern side, providing an important north–south transit route through the Alps.
  • E. A13
    A13 is a major road in England that serves as a key route linking London with areas in south Essex, including Basildon.
  • 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_69ca8329bb7c8190a63c643730839103 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbeb1ecc188190bbe2ab8d2423505b completed March 31, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce89bfb95c81909660460d5813fdaf completed April 2, 2026, 3:22 p.m.
Created at: March 30, 2026, 6:22 p.m.