Triple
T31953564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joint Counter Terrorist Centre facility |
E815844
|
entity |
| Predicate | holdsPrisoner |
P57303
|
FINISHED |
| Object | Helmut Zemo |
—
|
NE NERFINISHED |
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: Helmut Zemo | Statement: [Joint Counter Terrorist Centre facility, holdsPrisoner, Helmut Zemo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsPrisoner Context triple: [Joint Counter Terrorist Centre facility, holdsPrisoner, Helmut Zemo]
-
A.
prisonerOf
Indicates that one entity is held in custody or confinement by another entity, typically under legal or authoritative control.
-
B.
hasPrisoners
chosen
Indicates that an entity holds or contains one or more individuals who are imprisoned or detained.
-
C.
hasPrison
Indicates that one entity possesses, contains, or is the location of a prison associated with another entity.
-
D.
imprisonedWith
Indicates that two entities are confined or held in prison together at the same time and place.
-
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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2ad90b88190934e67fff4bffe58 |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:08 a.m.