Triple
T37540671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hallazeal the Ascended |
E933316
|
entity |
| Predicate | heroHealedByEffect |
P187900
|
FINISHED |
| Object | your hero |
—
|
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: your hero | Statement: [Hallazeal the Ascended, heroHealedByEffect, your hero]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heroHealedByEffect Context triple: [Hallazeal the Ascended, heroHealedByEffect, your hero]
-
A.
heroPowerEffect
Indicates the specific impact or outcome that a hero’s power has when it is used.
-
B.
healingAmount
chosen
Indicates the quantity of health or damage recovery provided by a healing action or effect.
-
C.
heroicStatus
Indicates that an entity possesses qualities or recognition associated with being a hero, such as bravery, selflessness, or notable heroic deeds.
-
D.
receivesSupernaturalHealingFrom
Indicates that one entity is restored to health or cured through a supernatural or miraculous intervention provided by another entity.
-
E.
defeatEffect
Indicates that one entity’s defeat causes a particular outcome or change to occur for another entity or the overall situation.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.