Triple
T37515048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duelist |
E932612
|
entity |
| Predicate | ascendancyClassType |
P188697
|
FINISHED |
| Object | melee damage specialist |
—
|
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: melee damage specialist | Statement: [Duelist, ascendancyClassType, melee damage specialist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ascendancyClassType Context triple: [Duelist, ascendancyClassType, melee damage specialist]
-
A.
ascendancyClass
Indicates a hierarchical or rank-based classification that specifies an entity’s superior or dominant status relative to others.
-
B.
typeOfAncestry
Indicates that one entity’s ancestry or lineage is characterized as being of a particular type or origin in relation to another entity.
-
C.
celestialClass
Indicates the classification relationship that assigns an entity to a particular type or category of celestial object.
-
D.
stellarClass
Indicates the spectral classification relationship between a star and its stellar class (e.g., O, B, A, F, G, K, M).
-
E.
notableRaceClass
Indicates that there exists a notable race or competition of a particular class or category associated with the subject.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
| PDg | Predicate description generation | batch_69fbacaea12c8190a4c99e64335f0e7e |
completed | May 6, 2026, 9:03 p.m. |
Created at: May 3, 2026, 4:17 p.m.