Triple
T37662510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Slowness |
E937746
|
entity |
| Predicate | canAffectThroughSplash |
P118698
|
FINISHED |
| Object | multiple entities |
—
|
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: multiple entities | Statement: [Potion of Slowness, canAffectThroughSplash, multiple entities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canAffectThroughSplash Context triple: [Potion of Slowness, canAffectThroughSplash, multiple entities]
-
A.
affectedByWaterAbsorb
Indicates that an entity’s state, behavior, or effectiveness is influenced or altered by another entity’s water-absorbing property or action.
-
B.
canAbsorbFire
Indicates the ability of one entity to take in, nullify, or withstand fire originating from another entity or source.
-
C.
canFall
Indicates that an entity has the potential or ability to fall or drop from a higher position to a lower one.
-
D.
hasEnvironmentalEffect
chosen
Indicates that one entity causes, contributes to, or is associated with an impact on the environment of another entity or context.
-
E.
canDrown
Indicates that one entity has the potential or ability to cause another entity to drown.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaa1321b48190af92a3e7ec24ec5b |
completed | May 6, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69fba8860f98819080b7bab05837b974 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.