Triple
T38584377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunwell Plateau |
E932312
|
entity |
| Predicate | originalLevelCap |
P99611
|
FINISHED |
| Object | 70 |
—
|
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: 70 | Statement: [Sunwell Plateau, originalLevelCap, 70]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalLevelCap Context triple: [Sunwell Plateau, originalLevelCap, 70]
-
A.
levelCapBefore
Indicates that one entity’s level limit or maximum allowable level must be reached or in place before the other entity’s level limit applies or can be attained.
-
B.
raisedLevelCapFrom
chosen
Indicates that an entity has increased a previously existing maximum level limit from a specified lower value.
-
C.
designedForLevelCap
Indicates that something is specifically created or configured to be suitable for use at a particular maximum level or level cap.
-
D.
raisesLevelCapTo
Indicates that one entity increases the maximum allowable level of another entity to a specified value.
-
E.
startingLevelMaximum
Indicates the highest allowable starting level or initial value that something can have at the beginning of a process or state.
- 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_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.