Triple

T22427526
Position Surface form Disambiguated ID Type / Status
Subject Rachelle Ann Go E554409 entity
Predicate spouse P13 FINISHED
Object Martin Spies NE NERFINISHED

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: Martin Spies | Statement: [Rachelle Ann Go, spouse, Martin Spies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martin Spies
Context triple: [Rachelle Ann Go, spouse, Martin Spies]
  • A. Martin Spies chosen
    Martin Spies is a relatively obscure individual whose primary public mention appears to be as a namesake in reference data, with no widely documented achievements or roles.
  • B. Jeffrey Spies
    Jeffrey Spies is a co-founder of the Center for Open Science and a prominent advocate for open, transparent, and reproducible scientific research practices.
  • C. Mike Spies
    Mike Spies is a former South African cricketer who played domestic first-class and List A cricket during the 1980s and early 1990s.
  • D. Simon Spies
    Simon Spies was a flamboyant Danish travel tycoon and founder of the charter airline Spies Rejser, known for revolutionizing package tourism in Scandinavia.
  • E. Jonathan Speirs
    Jonathan Speirs was a renowned Scottish architectural lighting designer known for co-founding influential lighting design practices and shaping the illumination of landmark buildings worldwide.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4f2d0c819091aa3558ea2ee630 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a2e438481908d43026727afa709 completed April 29, 2026, 1:09 a.m.
Created at: April 16, 2026, 8:47 p.m.