Triple
T37872331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isle of Thunder |
E944636
|
entity |
| Predicate | primaryRaid |
P204438
|
FINISHED |
| Object | Throne of Thunder |
E944644
|
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: Throne of Thunder | Statement: [Isle of Thunder, primaryRaid, Throne of Thunder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRaid Context triple: [Isle of Thunder, primaryRaid, Throne of Thunder]
-
A.
primaryFor
Indicates that one entity serves as the main or principal option, resource, or association for another entity among possible alternatives.
-
B.
primaryHeir
Indicates that one entity is the main or principal inheritor of another entity’s estate, title, or rights.
-
C.
primaryMount
Indicates that one entity serves as the main or default mount (attachment or support point) for another entity.
-
D.
primaryMode
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
E.
primaryFront
Indicates that one entity serves as the main or most important front-facing side or surface in relation to another entity.
- 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a410428ba9881909d78eef0d96bbfde |
completed | June 28, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_6a037a192a008190a9917688a9e804f4 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:19 p.m.