Triple
T38590033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neltharion's Tear |
E932431
|
entity |
| Predicate | associatedDragonAspect |
P206561
|
FINISHED |
| Object | Neltharion the Earth-Warder |
E2229005
|
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: Neltharion the Earth-Warder | Statement: [Neltharion's Tear, associatedDragonAspect, Neltharion the Earth-Warder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedDragonAspect Context triple: [Neltharion's Tear, associatedDragonAspect, Neltharion the Earth-Warder]
-
A.
portraysDragonAs
Indicates that one entity represents or depicts a dragon in a particular way, role, or characterization.
-
B.
typeOfDragon
Indicates the specific kind or category of dragon that an entity belongs to.
-
C.
usedDragon
Indicates that one entity employed or controlled a dragon to perform some action or fulfill a purpose.
-
D.
dragon
Indicates that an entity is a dragon or is classified as belonging to the category of dragons.
-
E.
dragonGuardian
Indicates that one entity serves as a protective guardian, specifically in the form or role of a dragon, over 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a42ca7f3b4c8190a1a1422da434124c |
completed | June 29, 2026, 7:41 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c85e308819083dd67b96f457659 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:32 p.m.