Triple
T32154082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Preppy Killer |
E821232
|
entity |
| Predicate | hasCrimeScene |
P183743
|
FINISHED |
| Object | Central Park area near Metropolitan Museum of Art |
—
|
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: Central Park area near Metropolitan Museum of Art | Statement: [Preppy Killer, hasCrimeScene, Central Park area near Metropolitan Museum of Art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCrimeScene Context triple: [Preppy Killer, hasCrimeScene, Central Park area near Metropolitan Museum of Art]
-
A.
hasCrimeInvestigation
Indicates that an entity is the subject of, or associated with, a formal investigation into a crime.
-
B.
hasCrimeElement
Indicates that a situation, action, or entity involves or contains a component that is legally recognized as part of a crime.
-
C.
hasMurderer
Indicates that one entity is the person who committed the murder of another entity.
-
D.
hasPartInMurderOf
Indicates involvement as a contributing participant in the commission of a murder.
-
E.
hasCourtroomScenes
Indicates that the work contains one or more scenes set in a courtroom or depicting courtroom proceedings.
- 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_69f34905e098819082191a6922a6d607 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7a283388c81908e4a9ee3369e8d6f |
completed | May 3, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69f7a06d4f108190bae3ab9ae431d2c7 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a224365081908ff6958e3b30bd05 |
completed | May 3, 2026, 7:29 p.m. |
Created at: May 1, 2026, 12:32 a.m.