Triple
T37511617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junkrat |
E932529
|
entity |
| Predicate | formerGameRole |
P100032
|
FINISHED |
| Object | Defense |
—
|
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: Defense | Statement: [Junkrat, formerGameRole, Defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerGameRole Context triple: [Junkrat, formerGameRole, Defense]
-
A.
formerCharacter
Indicates that an entity was once a character in a work or series but is no longer an active or current character.
-
B.
roleInGameplay
chosen
Indicates the specific function or responsibility an entity has within the context of gameplay or game mechanics.
-
C.
homeGameRole
Indicates that an entity participates in a game or match specifically in the role of the home side or host team.
-
D.
deFactoRole
Indicates that an entity effectively functions in a role or capacity in practice, even if that role is not formally or officially assigned.
-
E.
originGame
Indicates the game from which an entity, such as a character, item, or concept, originally comes.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00d6aff0a08190a330dd0c7c1352f9 |
completed | May 10, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_6a00d60f2a508190aeaf5a9d8af9c39e |
completed | May 10, 2026, 7:01 p.m. |
Created at: May 3, 2026, 4:17 p.m.