Triple
T12248038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Crow |
E291900
|
entity |
| Predicate | notableRelationshipDuration |
P47544
|
FINISHED |
| Object | longtime partner of Tony Bennett |
—
|
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: longtime partner of Tony Bennett | Statement: [Susan Crow, notableRelationshipDuration, longtime partner of Tony Bennett]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableRelationshipDuration Context triple: [Susan Crow, notableRelationshipDuration, longtime partner of Tony Bennett]
-
A.
relationshipDurationWith
chosen
Indicates the length of time that a specified relationship between two entities has existed or is expected to last.
-
B.
relationshipStartYear
Indicates the calendar year in which a particular relationship between entities was initiated.
-
C.
marriageDuration
Indicates the length of time that a marriage relationship has existed between two spouses.
-
D.
jointOccupationDuration
Indicates the length of time that two or more entities simultaneously share the same occupation or role.
-
E.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
- 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91d38ee10819093ed41d2954bf4ef |
completed | April 10, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69d91c46dcd88190a263db30804bff36 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.