Triple
T26032521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nd Cube |
E647471
|
entity |
| Predicate | gameDesignSpecialty |
P39812
|
FINISHED |
| Object | board-game-style mechanics |
—
|
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: board-game-style mechanics | Statement: [Nd Cube, gameDesignSpecialty, board-game-style mechanics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gameDesignSpecialty Context triple: [Nd Cube, gameDesignSpecialty, board-game-style mechanics]
-
A.
designedGame
Indicates that one entity is the creator or designer responsible for the conception and development of a particular game.
-
B.
gameModeDesign
Indicates that one entity defines or specifies the rules, structure, or configuration of a particular game mode for another entity.
-
C.
gameplayMechanic
chosen
Indicates a relationship where one entity functions as a rule, system, or interactive feature that defines how another entity can be played or operated within a game.
-
D.
boardGameGeekCategory
Indicates that something is classified under a specific category in the BoardGameGeek taxonomy of board game types or themes.
-
E.
gameFeatures
Indicates that a game includes or offers a particular element, characteristic, or functionality.
- 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_69e77e8b60e88190a3b26c4f0032a2c2 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6061b1b5081908dc5e2ac3ac58619 |
completed | May 2, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 9:06 a.m.