Triple
T24165721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John "Joker" Jackson |
E598977
|
entity |
| Predicate | situation |
P146005
|
FINISHED |
| Object | escaped prisoner |
—
|
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: escaped prisoner | Statement: [John "Joker" Jackson, situation, escaped prisoner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: situation Context triple: [John "Joker" Jackson, situation, escaped prisoner]
-
A.
situationType
Indicates the general kind or category of situation, event, or circumstance that a given instance represents.
-
B.
narrativeSituation
Indicates the contextual relationship that defines how events, characters, and perspectives are arranged and presented within a narrative.
-
C.
situationCountry
Indicates that a particular situation or event is associated with, occurs in, or pertains to a specific country.
-
D.
lifeSituation
chosen
Indicates the general circumstances, conditions, or context in which an entity’s life currently exists or unfolds.
-
E.
snapSituation
Indicates a situation or context in which a sudden, decisive, or snapshot-like event or state occurs between entities.
- 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_69e288cbd62881909de32ca64a70c17b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:32 p.m.