Triple
T31687114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dot Tattler |
E808689
|
entity |
| Predicate | conjoinedTwinType |
P42171
|
FINISHED |
| Object | dicephalic parapagus twin |
—
|
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: dicephalic parapagus twin | Statement: [Dot Tattler, conjoinedTwinType, dicephalic parapagus twin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conjoinedTwinType Context triple: [Dot Tattler, conjoinedTwinType, dicephalic parapagus twin]
-
A.
twinType
chosen
Indicates that one entity is classified as a specific type or category of twin in relation to another entity.
-
B.
twinning
Indicates that two entities are paired or linked as twins, typically sharing a formally recognized, parallel, or closely matched relationship.
-
C.
hasTwin
Indicates that one entity is a twin of another, sharing the same birth event or time with a sibling.
-
D.
hasTwinStatus
Indicates that an entity has a twin relationship or classification, such as being one of a pair of twins or having an associated twin counterpart.
-
E.
hasTwinCharacters
Indicates that two characters are twins, sharing the same parents and birth time or very close birth times.
- 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:07 p.m.