Triple

T13186735
Position Surface form Disambiguated ID Type / Status
Subject John Moresby E313874 entity
Predicate father P120 FINISHED
Object Fairfax Moresby E1026012 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: Fairfax Moresby | Statement: [John Moresby, father, Fairfax Moresby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fairfax Moresby
Context triple: [John Moresby, father, Fairfax Moresby]
  • A. Moresby chosen
    Moresby is an English surname most notably associated with Royal Navy officer John Moresby, after whom the city of Port Moresby in Papua New Guinea is named.
  • B. Elizabeth Bay
    Elizabeth Bay is a harbourside suburb in Sydney, Australia, known for its waterfront views, historic apartment buildings, and proximity to the city centre.
  • C. Moreton
    Moreton is a suburban area on the Wirral Peninsula in Merseyside, England, known for its residential character and coastal proximity.
  • D. Moreton
    Moreton is an English surname historically associated with British nobility, including figures such as Lady Byng of Vimy.
  • E. Nelson
    Nelson is a former mill town in Lancashire, England, known for its industrial heritage and location near the Pennine hills.
  • 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_69d806ae1e08819090d95bfe1538cc17 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c4b663c8190b0b18f0785f7b57d completed April 10, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff1581388190824a5377b64bd0ef completed May 3, 2026, 7:53 a.m.
Created at: April 9, 2026, 9:15 p.m.