Triple
T35975102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Balfour |
E1040389
|
entity |
| Predicate | sequelWorkAppearance |
P48180
|
FINISHED |
| Object | Catriona |
—
|
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: Catriona | Statement: [David Balfour, sequelWorkAppearance, Catriona]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sequelWorkAppearance Context triple: [David Balfour, sequelWorkAppearance, Catriona]
-
A.
sequelAppearsIn
Indicates that a sequel (such as a follow-up work or installment) is featured, shown, or occurs within a specified context or medium.
-
B.
hasSequelAppearance
chosen
Indicates that an entity appears again in a subsequent installment or sequel of a work.
-
C.
sequelWorkType
Indicates that the related work is a sequel and specifies the type or category of that sequel relationship between the works.
-
D.
sequelPerformer
Indicates that a performer participates in a work that is a sequel to a previous work.
-
E.
laterAppearancesIn
Indicates that one entity makes additional or subsequent appearances in relation to another entity after an initial occurrence.
- 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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7acaec1508190a38f2ac9cc5383e7 |
completed | May 3, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f7ab75387c819091afc3c2128eb903 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:07 p.m.