Triple
T24233949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol Vessey |
E601817
|
entity |
| Predicate | relationshipTypeWith Ed Stevens |
P142404
|
FINISHED |
| Object | on-again, off-again romance |
—
|
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: on-again, off-again romance | Statement: [Carol Vessey, relationshipTypeWith Ed Stevens, on-again, off-again romance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Ed Stevens Context triple: [Carol Vessey, relationshipTypeWith Ed Stevens, on-again, off-again romance]
-
A.
relationshipToStevens
Indicates a specified type of relationship that an entity has to the person or entity named Stevens.
-
B.
relationshipTypeWithStevens
chosen
Indicates the specific nature or category of the relationship that an entity has with Stevens.
-
C.
relationshipTypeWithEdwardDouglas
Indicates the specific nature or category of relationship that an entity has with Edward Douglas.
-
D.
relationshipTypeWith Hank Evans
Indicates the specific nature or category of the relationship that an entity has with Hank Evans.
-
E.
relationshipToEdwardBloom
Indicates the nature or type of connection an entity has to Edward Bloom, such as familial, social, or other relational ties.
- 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_69e29538aafc8190a2386fdebbd1393b |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f28a99889c819080efdec76be04646 |
completed | April 29, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:02 a.m.