Triple

T14532155
Position Surface form Disambiguated ID Type / Status
Subject Kew Railway Bridge E340941 entity
Predicate connects P390 FINISHED
Object Strand-on-the-Green E979111 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: Strand-on-the-Green | Statement: [Kew Railway Bridge, connects, Strand-on-the-Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Strand-on-the-Green
Context triple: [Kew Railway Bridge, connects, Strand-on-the-Green]
  • A. Strand-on-the-Green chosen
    Strand-on-the-Green is a picturesque riverside area in west London known for its historic houses, pubs, and scenic views along the River Thames.
  • B. Talbot Green
    Talbot Green is a retail and commercial village in Rhondda Cynon Taf, South Wales, known for its shopping centre and role as a local economic hub.
  • C. Winsted Green
    Winsted Green is a central public park and gathering space in Winsted, Connecticut, known for its historic and community significance.
  • D. Emersons Green
    Emersons Green is a suburban residential and commercial area on the outskirts of Bristol in South Gloucestershire, England.
  • E. Meriden Green
    Meriden Green is a central urban park and community gathering space in downtown Meriden, Connecticut, featuring open green areas, walking paths, and event venues.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea053f9bc8190901b9d321811d881 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a56872c8190a6d2421cb81aeeb1 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.