Triple
T28188621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McKinley |
E716240
|
entity |
| Predicate | primaryCompetitors |
P6615
|
FINISHED |
| Object | RISC server processors |
—
|
LITERAL 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: RISC server processors | Statement: [McKinley, primaryCompetitors, RISC server processors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryCompetitors Context triple: [McKinley, primaryCompetitors, RISC server processors]
-
A.
primaryCompetition
chosen
Indicates that one entity is the main or most significant competitor of another within a given market, domain, or context.
-
B.
underlyingCompanyMajorCompetitor
Indicates that one company serves as a primary or significant competitor to another company.
-
C.
primaryChallengers
Indicates that certain entities are the main or most significant opponents or competitors challenging another entity.
-
D.
competesWith
Indicates that two entities are in rivalry or opposition, each striving to outperform or gain advantage over the other in the same domain or objective.
-
E.
mainCompetitorNation
Indicates that one nation is the primary rival or chief competing nation of another.
- F. None of above.
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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a000a1d8fa88190a1d82ac746565c48 |
completed | May 10, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_6a0008b26eb88190ae03b2309a614774 |
completed | May 10, 2026, 4:25 a.m. |
Created at: April 27, 2026, 10:24 p.m.