Triple
T26989145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Cunanan |
E679817
|
entity |
| Predicate | activeYearsAsCriminal |
P104936
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Andrew Cunanan, activeYearsAsCriminal, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activeYearsAsCriminal Context triple: [Andrew Cunanan, activeYearsAsCriminal, 1997]
-
A.
activeYearsInCrime
chosen
Indicates the span of time during which an entity was actively involved in criminal activities.
-
B.
activeYearsWith
Indicates the span of time during which an entity was actively engaged in a particular role, activity, or association with another entity.
-
C.
startDateOfCriminalEvents
Indicates the date on which the referenced criminal events began or were first initiated.
-
D.
convictedOf
Indicates that a person or entity has been found guilty of committing a specified offense or crime through a formal legal process.
-
E.
ageAtTimeOfConvictionInStory
Indicates the age a person was at the specific time they were convicted within the context or timeline of the story.
- 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_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 6:50 a.m.