Triple
T30470401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Demi Moore pregnancy portrait for Vanity Fair (1991) |
E775275
|
entity |
| Predicate | subjectSpouseAtTime |
P181432
|
FINISHED |
| Object | Bruce Willis |
—
|
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: Bruce Willis | Statement: [Demi Moore pregnancy portrait for Vanity Fair (1991), subjectSpouseAtTime, Bruce Willis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectSpouseAtTime Context triple: [Demi Moore pregnancy portrait for Vanity Fair (1991), subjectSpouseAtTime, Bruce Willis]
-
A.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
B.
metSpouseAt
Indicates that one person first encountered or became acquainted with their spouse at a particular place, event, or time.
-
C.
spouseOfType
Indicates that one entity is the spouse of another, specifying the type or role of that spousal relationship.
-
D.
spouseNameAtTheTime
Indicates the name a person’s spouse had at the specific time relevant to the described event or record.
-
E.
spouseOfWork
Indicates that one person is the spouse of another specifically in the context of their workplace or professional environment.
- 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_69f2249622a48190b1fae2e3e4ee958a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
| PDg | Predicate description generation | batch_69f77648979c8190b6cdbb835ab8987c |
completed | May 3, 2026, 4:22 p.m. |
Created at: April 29, 2026, 8:11 p.m.