Triple
T37591790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zul'Gurub |
E935276
|
entity |
| Predicate | hasMountDrop |
P57946
|
FINISHED |
| Object | Swift Zulian Tiger |
—
|
NE NERFINISHED |
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: Swift Zulian Tiger | Statement: [Zul'Gurub, hasMountDrop, Swift Zulian Tiger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMountDrop Context triple: [Zul'Gurub, hasMountDrop, Swift Zulian Tiger]
-
A.
hasMount
Indicates that an entity is equipped with, riding, or otherwise using another entity as a mount for transportation or support.
-
B.
hasDropType
chosen
Indicates that an entity is associated with a specific type or category of drop (e.g., item, reward, or resource obtained).
-
C.
hasMountingFeature
Indicates that one entity includes or provides a structural feature intended for mounting or attaching another entity.
-
D.
hasMountingStyle
Indicates the method or configuration by which one entity is physically attached, fixed, or mounted to another surface or structure.
-
E.
hasDropTrack
Indicates that an entity includes or is associated with a track or section where a drop (sudden descent or fall) occurs.
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff9b1ad27081908f8a492396950795 |
completed | May 9, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69ff9a6354c48190ae21070c1424cb7a |
completed | May 9, 2026, 8:34 p.m. |
Created at: May 3, 2026, 4:18 p.m.