Triple
T26385113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winston Shakespeare |
E663255
|
entity |
| Predicate | firstMeetsCharacter |
P58222
|
FINISHED |
| Object | Stella Payne in Jamaica |
—
|
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: Stella Payne in Jamaica | Statement: [Winston Shakespeare, firstMeetsCharacter, Stella Payne in Jamaica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstMeetsCharacter Context triple: [Winston Shakespeare, firstMeetsCharacter, Stella Payne in Jamaica]
-
A.
firstMeets
chosen
Indicates that one entity encounters or comes into contact with another entity for the first time.
-
B.
meetsCharacterAtLocation
Indicates that one character encounters or comes together with another character at a specific location.
-
C.
capturesCharacter
Indicates that one entity seizes, traps, or takes control of another character.
-
D.
firstCharacterRules
Indicates that the entity associated with the first character in a sequence has authority, control, or priority over the others.
-
E.
firstCharacterType
Indicates that the type or category of the first character in a sequence or string has a specified value.
- 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_69ee88374adc81909868f3bab374a32f |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69fe38be079c8190a240191ac0e73e3a |
completed | May 8, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69fe350344508190930de2218156ca02 |
completed | May 8, 2026, 7:09 p.m. |
Created at: April 26, 2026, 11:21 p.m.