Triple
T19536750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Davina Windsor |
E488785
|
entity |
| Predicate | weddingAttendees |
P76666
|
FINISHED |
| Object | members of the British royal family |
—
|
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: members of the British royal family | Statement: [Lady Davina Windsor, weddingAttendees, members of the British royal family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weddingAttendees Context triple: [Lady Davina Windsor, weddingAttendees, members of the British royal family]
-
A.
guestAtWedding
chosen
Indicates that a person is attending or has attended a particular wedding as a guest.
-
B.
associatedWithWeddingOf
Indicates a relationship where something is connected or related to the wedding event of specific individuals.
-
C.
laterAttends
Indicates that one entity attends an event or place at a time later than another referenced attendance.
-
D.
eventParticipant
Indicates that an entity takes part in, is involved in, or participates in a particular event.
-
E.
hasGroom
Indicates that an entity has a groom, i.e., is associated with a male partner in a marriage or wedding 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6386f0fac819081bbc29172c8965e |
completed | April 20, 2026, 2:30 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.