Triple
T37464067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zilliax |
E930989
|
entity |
| Predicate | hasLifesteal |
P115461
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Zilliax, hasLifesteal, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLifesteal Context triple: [Zilliax, hasLifesteal, true]
-
A.
hasThornsEffect
Indicates that an entity causes damage or a harmful reaction back to another entity when it is touched, attacked, or otherwise interacted with, similar to being pricked by thorns.
-
B.
hasBurstDamagePotential
Indicates the extent to which an entity can inflict a large amount of damage in a short, concentrated period of time.
-
C.
killsOrIsKilledBy
Indicates that one entity causes the death of the other or is itself killed by that entity, capturing a mutual or directional lethal relationship between them.
-
D.
vampireAbility
chosen
Indicates that one entity possesses a supernatural power or trait specifically associated with being a vampire in relation to another entity or context.
-
E.
isUndead
Indicates that an entity is no longer living in a natural sense but continues to exist through supernatural or unnatural means.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff16775a9881909d26dbc1f0ef3e1c |
completed | May 9, 2026, 11:11 a.m. |
| PD | Predicate disambiguation | batch_69ff158e61708190a1c581d0d306cfce |
completed | May 9, 2026, 11:07 a.m. |
Created at: May 3, 2026, 4:17 p.m.