Triple
T29101772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sega Saturn light gun |
E736654
|
entity |
| Predicate | thirdPartyManufacturers |
P6378
|
FINISHED |
| Object | Mad Catz |
—
|
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: Mad Catz | Statement: [Sega Saturn light gun, thirdPartyManufacturers, Mad Catz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdPartyManufacturers Context triple: [Sega Saturn light gun, thirdPartyManufacturers, Mad Catz]
-
A.
thirdPlaceManufacturer
Indicates that the manufacturer is ranked third in position relative to other manufacturers in a specified context or competition.
-
B.
thirdParty
chosen
Indicates that an entity is a separate, external party involved in a relationship or transaction between two primary entities.
-
C.
thirdPartyVariants
Indicates that the subject entity has associated variants or alternative versions that are provided, managed, or defined by an external third party rather than by the primary source.
-
D.
manufacturerStatus
Indicates the current operational or business condition of a manufacturer in relation to the product or agreement in question.
-
E.
notableManufacturer
Indicates that an entity is a well-known or prominent producer or maker of another entity.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 28, 2026, 11:12 a.m.