Triple
T5621608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Colby |
E147617
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Colby |
E147617
|
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: Colby | Statement: [William Colby, familyName, Colby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Colby Context triple: [William Colby, familyName, Colby]
-
A.
Colby
chosen
Colby is a surname of English origin borne by various notable individuals, including former CIA Director William Colby.
-
B.
Colby Donaldson
Colby Donaldson is an American television personality and actor best known as a three-time contestant on the reality series "Survivor."
-
C.
Colby Parker Jr.
Colby Parker Jr. is a film editor known for his work on major Hollywood action and drama films, including the science fiction naval war movie "Battleship."
-
D.
Colton
Colton is a small city in Southern California’s Inland Empire region, located within San Bernardino County.
-
E.
Collen
Collen is a surname most notably associated with Nicki Collen, an American basketball coach.
- 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_69c00906f2a88190a992c66b13d606d4 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c022133eec819086acb04864dde5ee |
completed | March 22, 2026, 5:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04d59317c8190a4a3b186a46a7249 |
completed | March 22, 2026, 8:13 p.m. |
Created at: March 22, 2026, 3:40 p.m.