Triple
T26987758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cobra Organization |
E679778
|
entity |
| Predicate | primaryRoleInFranchise |
P16873
|
FINISHED |
| Object | main antagonist to G.I. Joe team |
—
|
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: main antagonist to G.I. Joe team | Statement: [Cobra Organization, primaryRoleInFranchise, main antagonist to G.I. Joe team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRoleInFranchise Context triple: [Cobra Organization, primaryRoleInFranchise, main antagonist to G.I. Joe team]
-
A.
roleInFranchiseHistory
Indicates the specific function, position, or contribution an entity has within the historical development or timeline of a franchise.
-
B.
franchiseOwner
Indicates that one entity holds the ownership and operating rights of a franchise granted by another entity.
-
C.
principalRoleIn
Indicates that an entity holds the primary or leading role in a particular context, activity, or relationship.
-
D.
hasFranchiseRole
Indicates that an entity holds a specific role or position within a franchise relationship.
-
E.
positionOnFranchise
chosen
Indicates the specific role, rank, or status an entity holds within a particular franchise or franchise-based organization.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69fee25dbca481909e6f1c255122b3a8 |
completed | May 9, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69fee1c8915c8190b08b63e42881f1a9 |
completed | May 9, 2026, 7:27 a.m. |
Created at: April 27, 2026, 6:49 a.m.