Triple
T18522821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donald Michie |
E452632
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Michie |
—
|
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: Michie | Statement: [Donald Michie, familyName, Michie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michie Context triple: [Donald Michie, familyName, Michie]
-
A.
Michie
chosen
Michie is a surname of Scottish origin borne by various notable individuals across fields such as sports, science, and the arts.
-
B.
Kuo
Kuo is a Wade–Giles romanization of the Chinese surname and name more commonly spelled "Guo" in pinyin.
-
C.
Kishi
Kishi is a Japanese surname borne by various notable figures in politics, arts, and entertainment.
-
D.
Kishi
Kishi is a locality within Nigeria’s Borgu region, known for its role in the area’s cultural and economic life.
-
E.
Heastie
Heastie is the surname of Carl E. Heastie, a prominent American politician who has served as Speaker of the New York State Assembly.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5338f6da48190bdb374019d10db05 |
completed | April 19, 2026, 7:57 p.m. |
Created at: April 10, 2026, 11:37 a.m.