Triple

T10616472
Position Surface form Disambiguated ID Type / Status
Subject Ian Mackley E276132 entity
Predicate spouse P13 FINISHED
Object Julian Clary E50190 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: Julian Clary | Statement: [Ian Mackley, spouse, Julian Clary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julian Clary
Context triple: [Ian Mackley, spouse, Julian Clary]
  • A. Julian Clary chosen
    Julian Clary is an English comedian, actor, novelist, and television personality known for his camp style and innuendo-laden humor.
  • B. Julian Clarke
    Julian Clarke is a Canadian film editor known for his work on major feature films, including the science fiction movie "Elysium."
  • C. Julian Osborn
    Julian Osborn is a key character in Nevil Shute’s post-apocalyptic novel "On the Beach," portrayed as a thoughtful and stoic Australian scientist confronting the inevitability of global nuclear fallout.
  • D. Julian Frampton
    Julian Frampton is a musician and the son of renowned English rock guitarist and singer Peter Frampton.
  • E. Julian Amery
    Julian Amery was a prominent British Conservative politician and minister known for his roles in defense and colonial affairs during the mid-20th century.
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df6d76dc8190bd8d481fed3225d9 completed April 8, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e215e3c3c88190833c1f56288629a2 completed April 17, 2026, 11:13 a.m.
Created at: April 8, 2026, 7:33 p.m.