Triple
T31213400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Living with Michael Jackson |
E795808
|
entity |
| Predicate | interviewedPerson |
P40000
|
FINISHED |
| Object | Michael Jackson |
—
|
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: Michael Jackson | Statement: [Living with Michael Jackson, interviewedPerson, Michael Jackson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interviewedPerson Context triple: [Living with Michael Jackson, interviewedPerson, Michael Jackson]
-
A.
interviewedBy
chosen
Indicates that an entity is the subject of an interview conducted by another entity.
-
B.
notableInterviewee
Indicates that a person has been interviewed by another person or organization in a way considered significant or noteworthy.
-
C.
testedPerson
Indicates that one entity has been subjected to a test, examination, or evaluation involving another entity.
-
D.
interviewees
Indicates that certain entities are the subjects or participants being questioned or evaluated in an interview process.
-
E.
usesInterviews
Indicates that one entity employs interviews as a method or tool in relation to another entity or process.
- 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_69f224d9d52c8190a61f68ded37fa755 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd2cf39b0c8190811b8a6fa9410560 |
completed | May 8, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69fd2ad8dd988190a9899701ba00d917 |
completed | May 8, 2026, 12:14 a.m. |
Created at: April 29, 2026, 9:09 p.m.