Triple
T38140853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Hazlewood |
E952474
|
entity |
| Predicate | marriedPartnerOfLoveInterest |
P33561
|
FINISHED |
| Object | Marion Taylor |
—
|
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: Marion Taylor | Statement: [Patrick Hazlewood, marriedPartnerOfLoveInterest, Marion Taylor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriedPartnerOfLoveInterest Context triple: [Patrick Hazlewood, marriedPartnerOfLoveInterest, Marion Taylor]
-
A.
spouseOrLover
Indicates a romantic partnership between two entities, whether formalized as a spouse or existing as a lover.
-
B.
unmarriedPartner
Indicates a relationship where one person is a romantic or domestic partner of another, and they are not legally married to each other.
-
C.
spouseAssociatedWith
chosen
Indicates a marital or spousal relationship or close association between two entities.
-
D.
possiblySpouse
Indicates that two entities may be spouses, reflecting an uncertain or hypothesized marital relationship between them.
-
E.
femalePartner
Indicates that one entity is the female partner in a romantic or marital relationship with the other entity.
- 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_69f76f09a7148190a4b91c0bacdc127a |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fe349879848190bcd77e3cc3470458 |
completed | May 8, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69fe31e3cf908190b23ebc2f7fe58722 |
completed | May 8, 2026, 6:56 p.m. |
Created at: May 3, 2026, 4:21 p.m.