Triple
T37229430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spacely Space Sprockets |
E923090
|
entity |
| Predicate | rivalCompanyOf |
P1375
|
FINISHED |
| Object | Cogswell Cogs |
—
|
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: Cogswell Cogs | Statement: [Spacely Space Sprockets, rivalCompanyOf, Cogswell Cogs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rivalCompanyOf Context triple: [Spacely Space Sprockets, rivalCompanyOf, Cogswell Cogs]
-
A.
underlyingCompanyMajorCompetitor
Indicates that one company serves as a primary or significant competitor to another company.
-
B.
rivalOf
Indicates a relationship in which two entities compete against or oppose each other, often seeking advantage in the same domain or objective.
-
C.
competesWith
chosen
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.
-
D.
competitorOwner
Indicates that one entity owns or controls a business or asset that competes in the same market or domain as another entity’s business or asset.
-
E.
laterBrandOf
Indicates that one brand is a subsequent or successor brand to another, coming into use at a later time.
- 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_69f76ea7f0008190b31b8e30f3d05a71 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.