Triple
T2215926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Armstrong |
E48032
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Craig |
E70284
|
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: Craig | Statement: [Craig Armstrong, givenName, Craig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craig Context triple: [Craig Armstrong, givenName, Craig]
-
A.
Craig
chosen
Craig is a masculine given name of Scottish origin that means "rock" or "crag."
-
B.
Neal
Neal is a masculine given name of Gaelic origin, commonly used in English-speaking countries.
-
C.
Craig Neal
Craig Neal is an American basketball coach and former player best known for serving as head coach of the University of New Mexico Lobos men's basketball team.
-
D.
Craig Barrett
Craig Barrett is an American business executive and engineer best known for serving as CEO and chairman of Intel Corporation.
-
E.
Craig Cannonier
Craig Cannonier is a Bermudian politician and member of the One Bermuda Alliance who served as Premier of Bermuda in the 2010s.
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbff11574819091d1b50d637ae767 |
completed | March 7, 2026, 6:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae65571b9481908f992cee85ee59eb |
completed | March 9, 2026, 6:14 a.m. |
Created at: March 4, 2026, 7:46 p.m.