Triple
T38147982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drak'Tharon Keep |
E952670
|
entity |
| Predicate | maxNormalLevel |
P75040
|
FINISHED |
| Object | 76 |
—
|
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: 76 | Statement: [Drak'Tharon Keep, maxNormalLevel, 76]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maxNormalLevel Context triple: [Drak'Tharon Keep, maxNormalLevel, 76]
-
A.
highestNorm
Indicates that the subject entity has the greatest norm (e.g., magnitude or size under a given norm) among a specified set of entities.
-
B.
higherNorm
Indicates that one entity has a greater magnitude, value, or norm than another entity.
-
C.
maxCurrent
Indicates the maximum electric current that is allowed to flow through or be drawn by an entity under specified conditions.
-
D.
maximumCeiling
chosen
Indicates the highest allowable or achievable limit or value that something cannot exceed.
-
E.
minimumLevel
Indicates that one entity specifies the lowest allowable or required level, degree, or threshold at which another entity, condition, or action becomes valid or applicable.
- 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_69f76f0a67f4819080c492f61d688fcc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.