Triple
T30094714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whizzer Brown |
E764830
|
entity |
| Predicate | relationshipTypeWithMarvin |
P203784
|
FINISHED |
| Object | on-again off-again romantic partner |
—
|
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 romantic partner | Statement: [Whizzer Brown, relationshipTypeWithMarvin, on-again off-again romantic partner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithMarvin Context triple: [Whizzer Brown, relationshipTypeWithMarvin, on-again off-again romantic partner]
-
A.
relationshipTypeWithMarnie
Indicates the specific nature or category of relationship that an entity has with Marnie.
-
B.
relationshipToMariane
Indicates the specific type of relationship or connection that an entity has to Mariane.
-
C.
relationshipStatusWithMarnie
Indicates the nature or current state of the relationship that an entity has with Marnie.
-
D.
relationshipToMarcy
Indicates that one entity has a specified personal or social relationship to Marcy.
-
E.
relationshipToDrLeoMarvin
Indicates the specific personal or professional connection an entity has with Dr. Leo Marvin.
- 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_69f22474e4288190b5f895fe3974aa92 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a020243e2b4819086dbfdcf4372405e |
completed | May 11, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_6a0200f585bc8190b774c54cec409b00 |
completed | May 11, 2026, 4:16 p.m. |
| PDg | Predicate description generation | batch_6a0202432fb08190abf6b83cd7da8deb |
completed | May 11, 2026, 4:22 p.m. |
Created at: April 29, 2026, 7:07 p.m.