Triple
T16462711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poltergeist |
E399845
|
entity |
| Predicate | previousRestraintType |
P122877
|
FINISHED |
| Object | over-the-shoulder restraints |
—
|
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: over-the-shoulder restraints | Statement: [Poltergeist, previousRestraintType, over-the-shoulder restraints]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousRestraintType Context triple: [Poltergeist, previousRestraintType, over-the-shoulder restraints]
-
A.
restraintType
Indicates the specific kind or method of restraint applied in a given situation or relationship.
-
B.
usesRestraints
Indicates that one entity applies or employs physical or procedural restraints on another entity.
-
C.
previousTractionType
Indicates the type of traction or traction method that was used previously before the current one.
-
D.
designedToConstrain
Indicates that one entity is intentionally created or configured to limit, restrict, or control the behavior, range, or properties of another entity.
-
E.
previousSettlementType
Indicates the type or classification of a settlement that existed at a location before the current or present settlement type.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32d824cd881909b1f2fd40e14ee35 |
completed | April 18, 2026, 7:06 a.m. |
| PD | Predicate disambiguation | batch_69e227048d608190a4205eae3117629a |
completed | April 17, 2026, 12:26 p.m. |
| PDg | Predicate description generation | batch_69e24556c1348190902a4d116c3137d9 |
completed | April 17, 2026, 2:36 p.m. |
Created at: April 10, 2026, 5:10 a.m.