Triple
T21253297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viktor Fasth |
E523798
|
entity |
| Predicate | caughtWith |
P108291
|
FINISHED |
| Object | left hand |
—
|
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: left hand | Statement: [Viktor Fasth, caughtWith, left hand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caughtWith Context triple: [Viktor Fasth, caughtWith, left hand]
-
A.
caughtBetween
Indicates being simultaneously subject to opposing forces, demands, or sides, unable to fully align with or escape either.
-
B.
catchStyle
chosen
Indicates the manner or technique with which something is caught (e.g., how an object, ball, or entity is captured or received).
-
C.
catches
Indicates that one entity successfully seizes, intercepts, or takes hold of another entity, often stopping its motion or preventing its escape.
-
D.
canBeCaughtWith
Indicates that one entity is capable of being captured, obtained, or discovered using another specified entity or method.
-
E.
heldCaptive
Indicates that one entity is being forcibly confined or restrained by another, preventing their freedom of movement or escape.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735a0391881908e45909e939415a5 |
completed | April 21, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69e5f61239708190ab7b3c83ae848a0d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:57 p.m.