Triple
T8875049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William McGregor |
E211254
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | McGregor |
E437051
|
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: McGregor | Statement: [William McGregor, familyName, McGregor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: McGregor Context triple: [William McGregor, familyName, McGregor]
-
A.
McGregor
chosen
McGregor is a Scottish surname most famously associated with the mixed martial artist Conor McGregor.
-
B.
Jocko
Jocko is a fictional character from the film "Red Dog," appearing as part of the story surrounding the legendary Australian kelpie.
-
C.
Mac McNeilly
Mac McNeilly is an American drummer best known for his powerful, driving work with the influential noise rock band The Jesus Lizard.
-
D.
O'Brien
O'Brien is a common Irish surname of Gaelic origin, historically associated with the descendants of the High King Brian Boru.
-
E.
Red Grant
Red Grant is a ruthless, psychopathic assassin and primary antagonist in the James Bond franchise, most prominently appearing as SPECTRE’s top killer in the film and novel "From Russia, with Love."
- 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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc614565788190aa14535760df88c8 |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0f9714c8190909587eecbb10e1a |
completed | April 3, 2026, 11:14 a.m. |
Created at: March 30, 2026, 6:52 p.m.