Triple
T37514992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Witch (Path of Exile) |
E932611
|
entity |
| Predicate | startingStatBias |
P92092
|
FINISHED |
| Object | high intelligence |
—
|
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: high intelligence | Statement: [Witch (Path of Exile), startingStatBias, high intelligence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingStatBias Context triple: [Witch (Path of Exile), startingStatBias, high intelligence]
-
A.
typicalPositionBias
Indicates a systematic tendency for something to be placed, chosen, or interpreted in a commonly favored or default position relative to other options.
-
B.
statValue
chosen
Indicates that an entity has a particular statistical attribute with a specified value.
-
C.
statFocus
Indicates that attention or emphasis is being directed toward a particular state, condition, or status of something.
-
D.
statisticalImpact
Indicates that one entity has a measurable effect on the statistical properties, outcomes, or metrics associated with another entity.
-
E.
statisticalStatus
Indicates that one entity represents the statistical condition, classification, or state of another entity within a quantitative or data-analysis context.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00d8ba18808190976682088a02a9a8 |
completed | May 10, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_6a00d85fad64819084f424ec8ecd3b57 |
completed | May 10, 2026, 7:11 p.m. |
Created at: May 3, 2026, 4:17 p.m.