Triple
T33728903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curtain: Poirot's Last Case |
E864219
|
entity |
| Predicate | featuresFictionalMurdererType |
P203815
|
FINISHED |
| Object | serial killer |
—
|
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: serial killer | Statement: [Curtain: Poirot's Last Case, featuresFictionalMurdererType, serial killer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFictionalMurdererType Context triple: [Curtain: Poirot's Last Case, featuresFictionalMurdererType, serial killer]
-
A.
fictionalKillerName
Indicates that an entity is known by a particular fictional name as a killer or murderer.
-
B.
hasSerialKiller
Indicates that one entity is a serial killer associated with, responsible for, or targeting another entity.
-
C.
fictionalAuthorVictim
Indicates that one entity is the author of a fictional work in which the other entity appears as a victim.
-
D.
hasFictionalDetective
Indicates that one entity (typically a work or series) features or includes a fictional detective character as part of its content.
-
E.
featuresFictionalCourtCase
Indicates that something includes or presents a court case that is fictional rather than real.
- F. None of above. chosen
Provenance (4 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_69f3498a64cc8190b4b414c67b280d93 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a020ec13d808190b41acdc31adc4191 |
completed | May 11, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_6a020d9259c08190ad0370091c23ea8a |
completed | May 11, 2026, 5:10 p.m. |
| PDg | Predicate description generation | batch_6a020ec02db481908ba6487e19c02491 |
completed | May 11, 2026, 5:15 p.m. |
Created at: May 1, 2026, 1:44 a.m.