Triple

T13249251
Position Surface form Disambiguated ID Type / Status
Subject A21 E315483 entity
Predicate passesNear P416 FINISHED
Object Robertsbridge E156837 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: Robertsbridge | Statement: [A21, passesNear, Robertsbridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robertsbridge
Context triple: [A21, passesNear, Robertsbridge]
  • A. Robertsbridge chosen
    Robertsbridge is a historic village in East Sussex, England, known for its medieval origins and rural setting in the Rother district.
  • B. Rotherbridge
    Rotherbridge is a small locality in West Sussex, England, situated near the River Rother and historically associated with a river crossing and surrounding rural landscape.
  • C. Gadebridge
    Gadebridge is a residential area and suburb of Hemel Hempstead in Hertfordshire, England.
  • D. Sowerby Bridge
    Sowerby Bridge is a market town in Calderdale, West Yorkshire, England, known for its industrial heritage, canal and railway junctions, and position in the Upper Calder Valley.
  • E. Horsebridge
    Horsebridge is a historic bridge spanning the River Tamar on the border between Devon and Cornwall in southwest England.
  • 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_69d806b1072881909e46bd212259c5f0 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98d9e7ea881908abc4b3a54896692 completed April 10, 2026, 11:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff37f7448190b9c555cae010d3b6 completed May 3, 2026, 7:54 a.m.
Created at: April 9, 2026, 9:24 p.m.