Triple
T36852461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cold Winter |
E910707
|
entity |
| Predicate | supportsSinglePlayerCampaign |
P43217
|
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: [Cold Winter, supportsSinglePlayerCampaign, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSinglePlayerCampaign Context triple: [Cold Winter, supportsSinglePlayerCampaign, true]
-
A.
hasSinglePlayer
chosen
Indicates that something includes, supports, or is designed for a single-player mode or experience.
-
B.
supportsInvasionMultiplayer
Indicates that a game or system allows and is compatible with invasion-style multiplayer gameplay, where other players can enter and disrupt one’s session.
-
C.
supportsOnlineMultiplayer
Indicates that the subject provides functionality for multiple users to play together over an online network.
-
D.
hasMultiplayerCoop
Indicates that an entity (such as a game or application) supports a multiplayer mode where multiple users can cooperate or play together simultaneously.
-
E.
hasMultiplayer
Indicates that an entity (such as a game or application) supports a mode where multiple users can participate or interact simultaneously.
- 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_69f76e8033d48190a59274f86f13be48 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.