Triple
T17781640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Dominique Bauby |
E443913
|
entity |
| Predicate | methodOfWriting |
P118124
|
FINISHED |
| Object | blinking his left eye |
—
|
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: blinking his left eye | Statement: [Jean-Dominique Bauby, methodOfWriting, blinking his left eye]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: methodOfWriting Context triple: [Jean-Dominique Bauby, methodOfWriting, blinking his left eye]
-
A.
mannerOfWriting
chosen
Indicates the way or style in which something is written or expressed in writing.
-
B.
writingForm
Indicates the specific script, notation, or written representation used to express a piece of language or content.
-
C.
isWrittenWith
Indicates that something is created or expressed using a particular writing tool, medium, or system.
-
D.
writingModel
Indicates that one entity serves as the writing system, script, or notation model used to represent the language or written content of another entity.
-
E.
canBeWrittenIn
Indicates that something is capable of being expressed, encoded, or represented using a particular language, notation, or medium.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4872152508190870a1765e0972ec1 |
completed | April 19, 2026, 7:41 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:12 a.m.