Triple
T4930345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Compaq Portable |
E110677
|
entity |
| Predicate | companyFoundedBy |
P11844
|
FINISHED |
| Object | Rod Canion |
E185094
|
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: Rod Canion | Statement: [Compaq Portable, companyFoundedBy, Rod Canion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rod Canion Context triple: [Compaq Portable, companyFoundedBy, Rod Canion]
-
A.
Rod Canion
chosen
Rod Canion is an American engineer and entrepreneur best known as a co-founder and the first CEO of Compaq Computer Corporation, a pioneering company in the personal computer industry.
-
B.
Ray Cusick
Ray Cusick was a British designer best known for creating the iconic look of the Daleks in the long-running science fiction television series Doctor Who.
-
C.
Jere Burns
Jere Burns is an American character actor known for his sharp, often villainous or darkly comedic roles in television series such as "Dear John," "Justified," and "Burn Notice."
-
D.
Bruce Cannon
Bruce Cannon is a film editor best known for his work on movies such as the 1993 drama "Poetic Justice."
-
E.
Brian Nelson
Brian Nelson is an American screenwriter best known for his work on the horror film "30 Days of Night" and the thriller "Hard Candy."
- 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_69bd4415190c8190817bee7ec9f9f944 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd703a0fa48190809b6ac3f2731349 |
completed | March 20, 2026, 4:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be89e731a4819087bf2e55215654d9 |
completed | March 21, 2026, 12:07 p.m. |
Created at: March 20, 2026, 1:30 p.m.