Triple
T38591048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HeroEngine (heavily modified) |
E932453
|
entity |
| Predicate | developerOfUsingProduct |
P120027
|
FINISHED |
| Object | BioWare Austin |
—
|
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: BioWare Austin | Statement: [HeroEngine (heavily modified), developerOfUsingProduct, BioWare Austin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developerOfUsingProduct Context triple: [HeroEngine (heavily modified), developerOfUsingProduct, BioWare Austin]
-
A.
developerOfGameUsed
Indicates that an entity is the developer of a game that is (or was) used or played in a given context.
-
B.
platformDeveloper
chosen
Indicates that one entity is the developer or creator responsible for building or maintaining the other entity as a platform.
-
C.
user
Indicates a relationship where an entity actively operates, controls, or interacts with another entity, typically as the primary agent or consumer of its function.
-
D.
developerOfWork
Indicates that one entity is the creator or producer responsible for making or developing a particular work.
-
E.
typeOfDeveloper
Indicates that one entity is a specific kind or category of developer in relation to 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe5ec9028081909ae3d6fbe2f4cbbc |
completed | May 8, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69fe5e1d715881909fc516fafc707644 |
completed | May 8, 2026, 10:05 p.m. |
Created at: May 3, 2026, 4:32 p.m.