Triple
T35010963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunset Sarsaparilla |
E1009937
|
entity |
| Predicate | inGameEffect |
P106972
|
FINISHED |
| Object | restores hit points |
—
|
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: restores hit points | Statement: [Sunset Sarsaparilla, inGameEffect, restores hit points]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inGameEffect Context triple: [Sunset Sarsaparilla, inGameEffect, restores hit points]
-
A.
eventEffect
Indicates the resulting change, outcome, or consequence that one event has on another state, entity, or event.
-
B.
visualEffect
Indicates that one entity produces, modifies, or is associated with a particular visual effect on another entity or within a scene.
-
C.
showsEffect
Indicates that one entity produces, demonstrates, or reveals a particular effect or outcome on another entity or context.
-
D.
providesEffect
chosen
Indicates that one entity causes, delivers, or produces a particular effect or outcome on another entity.
-
E.
temporaryEffect
Indicates that one entity causes or experiences an effect that is limited in duration and does not produce a lasting change.
- 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:01 p.m.