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.