Triple
T37421299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arkane Lyon |
E929858
|
entity |
| Predicate | hasSubsidiaryRelation |
P202049
|
FINISHED |
| Object | Arkane Austin (sister studio) |
E967119
|
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: Arkane Austin (sister studio) | Statement: [Arkane Lyon, hasSubsidiaryRelation, Arkane Austin (sister studio)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubsidiaryRelation Context triple: [Arkane Lyon, hasSubsidiaryRelation, Arkane Austin (sister studio)]
-
A.
hasSubsidiaryLabel
Indicates that one entity is identified as a subsidiary or subordinate organization of another entity.
-
B.
hasSubsidiariesIn
Indicates that an entity has subsidiary companies or organizations operating or registered in a specified location or jurisdiction.
-
C.
hasSubsidiaryTop
Indicates that one organization is the primary or top-level parent of another organization that operates as its subsidiary.
-
D.
hasSubsidiaryBusiness
Indicates that one business entity owns or controls another business entity as its subsidiary.
-
E.
usedBySubsidiaryOf
Indicates that something is used by an entity that is a subsidiary of another organization.
- F. None of above. chosen
Provenance (5 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_69f76ebf0f288190ba198a78341613b8 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0049e40d60819081e3899d8d9fca51 |
completed | May 10, 2026, 9:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41541c365c8190ac2281d7e811a7bf |
completed | June 28, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_6a0048c47b548190ad31b2901cc3784a |
completed | May 10, 2026, 8:58 a.m. |
| PDg | Predicate description generation | batch_6a0049e352248190b0a0bb7dfe572c2c |
completed | May 10, 2026, 9:03 a.m. |
Created at: May 3, 2026, 4:16 p.m.