Triple
T26989123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Cunanan |
E679817
|
entity |
| Predicate | placeOfMurderOfGianniVersace |
P64889
|
FINISHED |
| Object | Miami Beach, Florida, United States |
—
|
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: Miami Beach, Florida, United States | Statement: [Andrew Cunanan, placeOfMurderOfGianniVersace, Miami Beach, Florida, United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: placeOfMurderOfGianniVersace Context triple: [Andrew Cunanan, placeOfMurderOfGianniVersace, Miami Beach, Florida, United States]
-
A.
locatedInTheAdministrativeTerritorialEntityDuringAssassination
Indicates that an assassination took place while the subject was situated within a specified administrative territorial entity (such as a city, region, or country).
-
B.
assassinationAttemptLocation
Indicates the place where an attempted assassination occurred or was intended to occur.
-
C.
locationOfFirstPerformanceDuringAssassination
Indicates the place where a work or performance was first presented at the time an assassination occurred.
-
D.
placeOfKilling
chosen
Indicates the location where a killing event took place.
-
E.
assassinatedIn
Indicates that an assassination of one entity occurred within the specified location or context represented by another entity.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6b2a65c7c8190ac40f1466ceadefc |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 27, 2026, 6:50 a.m.