Triple

T20779191
Position Surface form Disambiguated ID Type / Status
Subject Samuel Liddell MacGregor Mathers E511434 entity
Predicate givenName P17 FINISHED
Object MacGregor 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: MacGregor | Statement: [Samuel Liddell MacGregor Mathers, givenName, MacGregor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MacGregor
Context triple: [Samuel Liddell MacGregor Mathers, givenName, MacGregor]
  • A. MacGregor chosen
    MacGregor is a Scottish surname historically associated with Clan Gregor and borne by various notable figures in culture, politics, and sports.
  • B. MacNaught
    MacNaught is a Scottish surname associated as a sept with Clan MacNaughton.
  • C. MacClure
    MacClure is a surname, a spelling variant of McClure, borne by various individuals of Scottish and Irish origin.
  • D. Skaife
    Skaife is the surname of Mark Skaife, a prominent Australian racing driver and multiple Supercars Championship winner.
  • E. MacLeod
    MacLeod is a Scottish surname historically associated with the Highlands and the Isle of Skye, borne by various notable figures in politics, arts, and public life.
  • 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_69e0b4cac7a48190a715cb3d545df2b4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26ed1a08190bb73824672328d98 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.