Triple

T23435653
Position Surface form Disambiguated ID Type / Status
Subject Stonehenge tunnel E563452 entity
Predicate usesRoad P20522 FINISHED
Object A303 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: A303 | Statement: [Stonehenge tunnel, usesRoad, A303]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A303
Context triple: [Stonehenge tunnel, usesRoad, A303]
  • A. A303 chosen
    The A303 is a major trunk road in southern England that links the M3 motorway near Basingstoke to the A30 in Devon, passing close to landmarks such as Stonehenge.
  • B. A30
    The A30 is a major trunk road in southern England that runs from London to Land's End in Cornwall, serving as an important route across the southwest.
  • C. A302
    A302 is a key section of London's Inner Ring Road, linking central routes across Westminster and the South Bank.
  • D. A307
    A307 is a designated A-class road number in the United Kingdom’s road network.
  • E. A33
    A33 is a major road in southern England that runs between Reading and Southampton, serving as an important regional transport route.
  • 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_69e24553980c8190bb66a2ae0bdab125 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5dbdf248190a09e971f2718d01f completed April 29, 2026, 6:31 a.m.
Created at: April 17, 2026, 5:50 p.m.