Triple
T35975099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Balfour |
E1040389
|
entity |
| Predicate | titleOfWorkFirstAppearance |
P115164
|
FINISHED |
| Object | Kidnapped |
—
|
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: Kidnapped | Statement: [David Balfour, titleOfWorkFirstAppearance, Kidnapped]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleOfWorkFirstAppearance Context triple: [David Balfour, titleOfWorkFirstAppearance, Kidnapped]
-
A.
firstAppearedInWorkBy
Indicates that an entity made its first appearance within a specific work created by a particular author or creator.
-
B.
firstAppearanceBook
chosen
Indicates the book in which an entity (such as a character or concept) is first introduced or appears.
-
C.
firstAppearancePublisher
Indicates the publisher responsible for releasing an entity’s first appearance.
-
D.
firstAppearancePublisherImprint
Indicates the publishing imprint under which an entity (such as a work or character) was first released or made its initial appearance.
-
E.
firstMagazineAppearance
Indicates that an entity made its debut or earliest known appearance in a particular magazine.
- 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_69ff965f9be48190b015b788207be676 |
completed | May 9, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69ff95d3015c8190b9d293fe31b859c3 |
completed | May 9, 2026, 8:15 p.m. |
Created at: May 3, 2026, 4:07 p.m.