Triple
T37599885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elwynn Forest |
E935493
|
entity |
| Predicate | factionDominance |
P192686
|
FINISHED |
| Object | Alliance |
—
|
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: Alliance | Statement: [Elwynn Forest, factionDominance, Alliance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: factionDominance Context triple: [Elwynn Forest, factionDominance, Alliance]
-
A.
factionTerritory
chosen
Indicates that a specific geographic area or domain is controlled, claimed, or governed by a particular faction.
-
B.
partyDominance
Indicates that one political party holds a prevailing or controlling position over others within a given political context or system.
-
C.
divisionDominance
Indicates that one entity holds a superior or controlling position over another within an organizational or functional division.
-
D.
factionInfluence
Indicates the degree to which one faction affects, controls, or shapes the behavior, decisions, or status of another entity or group.
-
E.
factionCount
Indicates the number of distinct factions associated with or involved in a given context or entity.
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd32848ea88190a71e6df402bbb30e |
completed | May 8, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69fd2d7e95588190991d5f21e25155df |
completed | May 8, 2026, 12:25 a.m. |
Created at: May 3, 2026, 4:18 p.m.