Triple
T31453460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgina Evers-Swindell |
E802384
|
entity |
| Predicate | partnerInBoat |
P171891
|
FINISHED |
| Object | Caroline Evers-Swindell |
—
|
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: Caroline Evers-Swindell | Statement: [Georgina Evers-Swindell, partnerInBoat, Caroline Evers-Swindell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partnerInBoat Context triple: [Georgina Evers-Swindell, partnerInBoat, Caroline Evers-Swindell]
-
A.
partnerInMission
Indicates that two or more entities collaborate as partners in carrying out the same mission or operation.
-
B.
partnerInUnionWith
Indicates a mutual partnership or union relationship between two entities, such as a civil, domestic, or similar legally or socially recognized union.
-
C.
isTwinRowingPartnerOf
chosen
Indicates that two individuals are twin siblings who row together as partners in a rowing team or boat.
-
D.
hasCoxswain
Indicates that a rowing crew or boat is assigned a coxswain who steers and directs it.
-
E.
partnerInLoveTeam
Indicates that two entities are teammates who are also partners in a romantic or love-based relationship.
- 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_69f348c678ac81908a2e950867619061 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 30, 2026, 9:14 p.m.