Triple
T35297106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Johnny Boz |
E1019401
|
entity |
| Predicate | policeCaseStatusInNarrative |
P115377
|
FINISHED |
| Object | unsolvedAtStart |
—
|
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: unsolvedAtStart | Statement: [murder of Johnny Boz, policeCaseStatusInNarrative, unsolvedAtStart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policeCaseStatusInNarrative Context triple: [murder of Johnny Boz, policeCaseStatusInNarrative, unsolvedAtStart]
-
A.
narrativeStatus
Indicates the role or state of an element within a narrative, such as whether it is current, hypothetical, background, or otherwise positioned in the story’s progression.
-
B.
statusInColumbo
Indicates that an entity holds a particular status, role, or condition specifically within the context of Columbo.
-
C.
publicNarrative
Indicates that an entity communicates or frames a story, message, or account intended for a public audience.
-
D.
hasCauseNarrative
Indicates that one entity provides a narrative or explanatory account of the cause or causal background of another entity or event.
-
E.
investigationStatus
chosen
Indicates the current state or phase of an ongoing or completed investigation.
- 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_69f76de7eedc8190a3bdc64ebbc05b42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:03 p.m.