Triple
T38611552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri Charrière |
E934494
|
entity |
| Predicate | autobiographicalSubject |
P58275
|
FINISHED |
| Object | his imprisonment in French Guiana |
—
|
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: his imprisonment in French Guiana | Statement: [Henri Charrière, autobiographicalSubject, his imprisonment in French Guiana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: autobiographicalSubject Context triple: [Henri Charrière, autobiographicalSubject, his imprisonment in French Guiana]
-
A.
hasAutobiographicalSubject
chosen
Indicates that something (such as a work, text, or narrative) has a subject that is the author or creator’s own life or personal experiences.
-
B.
wroteAutobiographicalWork
Indicates that a person is the author of a written work that is an account of their own life.
-
C.
memoirAuthor
Indicates that one entity is the author or writer of the other entity, which is a memoir.
-
D.
biographicalSubjectTitle
Indicates that a title or role is used as the biographical subject of a work or biographical description.
-
E.
hasBiographicalSubjectRole
Indicates that a role is the biographical subject of a biographical work or account.
- 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_69f76eccd6d081909ccce171011739a1 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdb0de8c08190928cd1323f80ab5c |
completed | May 7, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69fcd9017dd88190b32a73fe78909740 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.