Triple

T11522321
Position Surface form Disambiguated ID Type / Status
Subject A38 road E273195 entity
Predicate passesThrough P225 FINISHED
Object Birmingham E13669 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: Birmingham | Statement: [A38 road, passesThrough, Birmingham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Birmingham
Context triple: [A38 road, passesThrough, Birmingham]
  • A. Birmingham chosen
    Birmingham is a major industrial city in England’s West Midlands, historically significant for its manufacturing heritage and heavy bombing during the Second World War.
  • B. Birmingham
    Birmingham is a major industrial and cultural city in the southern United States, known historically for its steel production and pivotal role in the Civil Rights Movement.
  • C. Manchester
    Manchester is a major city in northwest England known for its industrial heritage, vibrant cultural scene, and influential contributions to music, sport, and science.
  • D. Manchester
    Manchester is the most populous city in the U.S. state of New Hampshire and a major economic and cultural center for the region.
  • E. Manchester
    Manchester is a historic neighborhood on Pittsburgh’s North Side known for its 19th-century architecture and designation as a historic district.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fd129c88190893b95222480e04a completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e68508d3ac8190888982eca2472919 completed April 20, 2026, 7:56 p.m.
Created at: April 8, 2026, 9:37 p.m.