Triple
T36852016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avatar: Frontiers of Pandora |
E910697
|
entity |
| Predicate | hasMultiplayerCoop |
P197343
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Avatar: Frontiers of Pandora, hasMultiplayerCoop, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMultiplayerCoop Context triple: [Avatar: Frontiers of Pandora, hasMultiplayerCoop, true]
-
A.
hasMultiplayer
Indicates that an entity (such as a game or application) supports a mode where multiple users can participate or interact simultaneously.
-
B.
supportsOnlineMultiplayer
Indicates that the subject provides functionality for multiple users to play together over an online network.
-
C.
multiplayerCompatibleWith
Indicates that two or more entities can function together in a shared multiplayer context without conflict or incompatibility.
-
D.
multiplayerFeature
Indicates that the subject supports or involves multiple users participating together, typically at the same time within the same activity or environment.
-
E.
supportsLocalMultiplayer
Indicates that the subject provides functionality for multiple players to play together on the same device or local network.
- F. None of above. chosen
Provenance (4 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_69f76e8033d48190a59274f86f13be48 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe87b609888190913b0c3f787ecdba |
completed | May 9, 2026, 1:02 a.m. |
| PD | Predicate disambiguation | batch_69fe8731af48819092084f6f74bf052d |
completed | May 9, 2026, 1 a.m. |
| PDg | Predicate description generation | batch_69fe87b52bd4819087d6d338fe47c97c |
completed | May 9, 2026, 1:02 a.m. |
Created at: May 3, 2026, 4:13 p.m.