Triple
T38590661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyur |
E932444
|
entity |
| Predicate | canChooseStartingCityState |
P22794
|
FINISHED |
| Object | Ul'dah |
—
|
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: Ul'dah | Statement: [Hyur, canChooseStartingCityState, Ul'dah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canChooseStartingCityState Context triple: [Hyur, canChooseStartingCityState, Ul'dah]
-
A.
startCity
chosen
Indicates the city where a journey, route, or transportation service begins.
-
B.
hasTargetCity
Indicates that something is directed toward, intended for, or specifically associated with a particular city as its target.
-
C.
isCityState
Indicates that one entity is a city located within, and politically or administratively belonging to, the state represented by the other entity.
-
D.
containsCityState
Indicates that one entity includes or encompasses a specific city and state within its scope or boundaries.
-
E.
startStateOrTerritory
Indicates the state or territory in which an event, process, or relationship begins or is initially situated.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.