Triple
T37554377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judgement Legplates |
E933659
|
entity |
| Predicate | originalGamePhase |
P75603
|
FINISHED |
| Object | original level 60 raiding |
—
|
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: original level 60 raiding | Statement: [Judgement Legplates, originalGamePhase, original level 60 raiding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalGamePhase Context triple: [Judgement Legplates, originalGamePhase, original level 60 raiding]
-
A.
hasPhaseOfPlay
chosen
Indicates a relationship where a broader game or activity includes or is associated with a specific phase or segment of play.
-
B.
gameState
Indicates the current status or condition of a game at a particular point in time, including relevant rules, progress, and contextual information.
-
C.
commonRacePhase
Indicates that two or more race events share the same phase or stage within a larger racing sequence or structure.
-
D.
stateGame6
Indicates that an entity is in the specific condition or configuration labeled as "game6" within a set of game-related states.
-
E.
mainGame
Indicates the primary or central game associated with an entity, distinguishing it from secondary or related games.
- 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_69f76eca55bc8190acf25741793d5dac |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.