Triple
T37539042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azuremyst Isle |
E933279
|
entity |
| Predicate | raceTheme |
P188217
|
FINISHED |
| Object | Draenei |
E2228310
|
NE 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: Draenei | Statement: [Azuremyst Isle, raceTheme, Draenei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceTheme Context triple: [Azuremyst Isle, raceTheme, Draenei]
-
A.
vehicleTheme
Indicates that an entity serves as the vehicle or means through which another entity, event, or action is carried out or expressed.
-
B.
raceComponent
Indicates that one entity is a constituent part, segment, or stage within a larger race or racing event involving another entity.
-
C.
raceFeatured
Indicates that a particular race or racing event is prominently highlighted or given special attention within a context, such as a program, schedule, or media coverage.
-
D.
raceCategory
Indicates the classification of an entity into a specific race or racial group within a defined categorization system.
-
E.
featuresRaceBetween
Indicates that an event or context includes or showcases a competitive race occurring between participants.
- F. None of above. chosen
Provenance (5 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40ba3dd2e881908b0a846ad55a8066 |
completed | June 28, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
| PDg | Predicate description generation | batch_69fba5ee00fc81909be7b947a3f95034 |
completed | May 6, 2026, 8:34 p.m. |
Created at: May 3, 2026, 4:17 p.m.