Triple
T20894960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clearwire Corporation |
E514508
|
entity |
| Predicate | keyPerson |
P256
|
FINISHED |
| Object | Craig McCaw |
—
|
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: Craig McCaw | Statement: [Clearwire Corporation, keyPerson, Craig McCaw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craig McCaw Context triple: [Clearwire Corporation, keyPerson, Craig McCaw]
-
A.
Craig McCaw
chosen
Craig McCaw is an American telecommunications entrepreneur best known for pioneering the cellular phone industry through McCaw Cellular Communications.
-
B.
Marion Oliver McCaw
Marion Oliver McCaw was a Seattle philanthropist whose major donation supported the creation of the performing arts venue that bears her name.
-
C.
Ian McCaw
Ian McCaw is an American college athletics administrator known for serving as the athletic director at multiple universities, including Liberty University and previously Baylor University.
-
D.
Bernard Widrow
Bernard Widrow is an American electrical engineer and pioneer in adaptive signal processing and neural networks, best known for co-inventing the LMS algorithm and Widrow-Hoff learning rule.
-
E.
John Gage
John Gage is a name shared by several notable figures, including historical politicians, diplomats, and fictional characters in film and television.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d06129788190b88ab807af4641c1 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:47 p.m.