Triple
T37707380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Poison |
E939230
|
entity |
| Predicate | effectOnMostMobs |
P196530
|
FINISHED |
| Object | reduces health to a minimum threshold |
—
|
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: reduces health to a minimum threshold | Statement: [Potion of Poison, effectOnMostMobs, reduces health to a minimum threshold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnMostMobs Context triple: [Potion of Poison, effectOnMostMobs, reduces health to a minimum threshold]
-
A.
effectOnUndead
Indicates the specific impact or influence that something has on undead entities, such as harming, healing, controlling, or otherwise altering them.
-
B.
effectivenessAgainst
Indicates how well one entity performs in countering, influencing, or mitigating the impact of another entity.
-
C.
attackEffect
Indicates that one entity’s attack produces a specific effect or consequence on another entity.
-
D.
effectOnGhosts
Indicates the influence or impact that something has on ghosts, such as how it alters their state, behavior, or abilities.
-
E.
effectCount
Indicates the number of distinct effects or outcomes associated with a given action, event, or entity.
- F. None of above. chosen
Provenance (4 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_69f76edb49dc8190b951dce9ce6ef789 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
| PDg | Predicate description generation | batch_69fe59d03a648190bbe846cb5730a477 |
completed | May 8, 2026, 9:46 p.m. |
Created at: May 3, 2026, 4:18 p.m.