Triple
T38643966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Void Elves |
E938669
|
entity |
| Predicate | startingLevelArea |
P100143
|
FINISHED |
| Object | Telogrus Rift |
—
|
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: Telogrus Rift | Statement: [Void Elves, startingLevelArea, Telogrus Rift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingLevelArea Context triple: [Void Elves, startingLevelArea, Telogrus Rift]
-
A.
hasStartingArea
Indicates that an entity is associated with, or begins from, a specific initial area or region.
-
B.
startingLevelRange
Indicates the range of initial levels at which an entity, activity, or state begins.
-
C.
gameLevelLocation
Indicates the specific in-game location or area where a particular game level takes place or is situated.
-
D.
startingLevelMaximum
Indicates the highest allowable starting level or initial value that something can have at the beginning of a process or state.
-
E.
startingZoneFor
chosen
Indicates the zone or area where an entity initially begins, is placed, or starts its activity or process.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a018f9c7cf88190adc5daf3806f2077 |
completed | May 11, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_6a018ca4e0e481908091f0c1f8a4c31b |
completed | May 11, 2026, 8 a.m. |
Created at: May 3, 2026, 4:32 p.m.