Triple

T13902560
Position Surface form Disambiguated ID Type / Status
Subject George Sands E334261 entity
Predicate worksAt P7 FINISHED
Object Bristol hospital E1068753 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: Bristol hospital | Statement: [George Sands, worksAt, Bristol hospital]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bristol hospital
Context triple: [George Sands, worksAt, Bristol hospital]
  • A. Bristol hospital chosen
    Bristol hospital is a medical facility in Bristol, England, providing healthcare services to the local community and surrounding region.
  • B. Queen Elizabeth's Hospital, Bristol
    Queen Elizabeth's Hospital, Bristol is a historic independent day school for boys in Bristol, England, known for its long-standing academic tradition and notable alumni.
  • C. Bath General Hospital
    Bath General Hospital is an 18th-century medical institution in Bath, England, renowned as a prominent example of Georgian architecture.
  • D. Brompton Hospital
    Brompton Hospital, formally the Royal Brompton Hospital, is a leading specialist heart and lung hospital in London, renowned for its cardiothoracic care and research.
  • E. Morriston Hospital
    Morriston Hospital is a major teaching and acute care hospital in Swansea, Wales, providing a wide range of specialist and emergency medical services for the region.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de25d9c7a48190ad8fb0ca676f4f7b completed April 14, 2026, 11:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce7638a88190aae1b59c00ee27ce completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:16 p.m.