Triple
T38583312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zandalari trolls |
E932291
|
entity |
| Predicate | otherZones |
P191220
|
FINISHED |
| Object | Nazmir |
E2276195
|
NE 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: Nazmir | Statement: [Zandalari trolls, otherZones, Nazmir]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: otherZones Context triple: [Zandalari trolls, otherZones, Nazmir]
-
A.
zone
Indicates that an entity is located within, associated with, or assigned to a particular geographic or conceptual area or zone.
-
B.
coreZoneArea
Indicates the area or spatial extent of a designated core zone within a larger region or system.
-
C.
zonedTo
Indicates that one entity is assigned or designated to fall within the jurisdiction, service area, or regulatory zone of another entity.
-
D.
formerZone
Indicates that an entity was previously designated as a particular zone or area but no longer holds that status.
-
E.
factionZoneFor
Indicates that a specific area or zone is designated as belonging to, controlled by, or associated with a particular faction.
- F. None of above. chosen
Provenance (5 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_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41f43924cc8190b03f5c8d442f4e7f |
completed | June 29, 2026, 4:27 a.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcdaa2bfc08190beccabb0f1782d0d |
completed | May 7, 2026, 6:32 p.m. |
Created at: May 3, 2026, 4:32 p.m.