Triple
T34630624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlanta Exes |
E889269
|
entity |
| Predicate | featuresExSpouseConnection |
P204238
|
FINISHED |
| Object | Usher |
E64985
|
NE 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: Usher | Statement: [Atlanta Exes, featuresExSpouseConnection, Usher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresExSpouseConnection Context triple: [Atlanta Exes, featuresExSpouseConnection, Usher]
-
A.
hasMemberSpouseConnection
Indicates a relationship where one entity is a spouse of a member associated with the other entity.
-
B.
spouseCharacteristic
Indicates that a particular characteristic, trait, or attribute is associated with a person’s spouse within the relationship.
-
C.
spouseFatherMemberOf
Indicates that the father of a person’s spouse is a member of a specified group, organization, or entity.
-
D.
spouseMemberOf
Indicates that a person’s spouse is a member of a specified group, organization, or entity.
-
E.
spouseInFamily
Indicates that a person is a spouse (married partner) within the context of a specific family unit.
- F. None of above. chosen
Provenance (5 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_69f349d64a388190a013cfa9bd33fad7 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0353887e848190ad98ecbbe7bbc061 |
completed | May 12, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37412367ec81909eed5d2a24e872f3 |
completed | June 21, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_6a0352dfb5648190b9f8c9b7c388d2a1 |
completed | May 12, 2026, 4:18 p.m. |
| PDg | Predicate description generation | batch_6a0353877d4c8190a461118bc66d6b09 |
completed | May 12, 2026, 4:21 p.m. |
Created at: May 1, 2026, 2:04 a.m.