Triple
T38585205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patch 2.1 – Black Temple |
E932330
|
entity |
| Predicate | introducedFaction |
P125059
|
FINISHED |
| Object | Ogri'la |
—
|
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: Ogri'la | Statement: [Patch 2.1 – Black Temple, introducedFaction, Ogri'la]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducedFaction Context triple: [Patch 2.1 – Black Temple, introducedFaction, Ogri'la]
-
A.
introducesFaction
chosen
Indicates that one entity is responsible for presenting, bringing into play, or formally establishing a faction within a given context or setting.
-
B.
expansionFaction
Indicates a relationship where one faction is the expanding or outward-growing counterpart of another faction.
-
C.
factionFounded
Indicates that an organization or group was established or created by a particular faction.
-
D.
weakenedFaction
Indicates that one faction has reduced the strength, influence, or effectiveness of another faction.
-
E.
factionName
Indicates the specific name assigned to a faction with which an entity is associated.
- 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_69ff27b125948190aced0fe0189fd39a |
completed | May 9, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69ff26c30a0481909ef6a54ded851e42 |
completed | May 9, 2026, 12:21 p.m. |
Created at: May 3, 2026, 4:32 p.m.