Triple
T38590015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neltharion's Tear |
E932431
|
entity |
| Predicate | statBonus |
P167558
|
FINISHED |
| Object | +44 Spell Damage |
—
|
LITERAL 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: +44 Spell Damage | Statement: [Neltharion's Tear, statBonus, +44 Spell Damage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statBonus Context triple: [Neltharion's Tear, statBonus, +44 Spell Damage]
-
A.
damageBonus
chosen
Indicates that an entity receives an additional amount of damage dealt beyond its base damage value.
-
B.
strengthFeat
Indicates that an entity performs or demonstrates a notable feat of physical strength in relation to another entity or object.
-
C.
supportsBonus
Indicates that one entity provides or enables an additional benefit, reward, or bonus for another entity.
-
D.
awardEffect
Indicates that one entity confers or grants a benefit, recognition, or reward that has a particular impact or consequence on another entity.
-
E.
statBlocks
Indicates that one entity provides or contains statistical blocks or structured stat information about another 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.