Triple
T35806660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chokeslam |
E1035117
|
entity |
| Predicate | commonSetup |
P28573
|
FINISHED |
| Object | goozle (one-handed throat grab) |
—
|
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: goozle (one-handed throat grab) | Statement: [Chokeslam, commonSetup, goozle (one-handed throat grab)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonSetup Context triple: [Chokeslam, commonSetup, goozle (one-handed throat grab)]
-
A.
canonicalSetup
Indicates that an entity is arranged or configured in its standard, officially accepted, or authoritative form.
-
B.
typicalSetup
chosen
Indicates that an entity is arranged, configured, or organized in its standard or commonly used setup relative to another entity or context.
-
C.
commonTest
Indicates that two or more entities share the same test, testing procedure, or evaluation in common.
-
D.
setUp
Indicates establishing, arranging, or preparing something so that it is ready for use or for a particular purpose.
-
E.
commonModules
Indicates that two or more entities share one or more identical or overlapping modules in common.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fedfd913f48190bdcd450980868d9a |
completed | May 9, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fedf58c6e88190821a7156054c9086 |
completed | May 9, 2026, 7:16 a.m. |
Created at: May 3, 2026, 4:06 p.m.