Triple
T24860460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lydia Davis |
E622136
|
entity |
| Predicate | notableAuthorTranslated |
P141041
|
FINISHED |
| Object | Marcel Proust |
—
|
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: Marcel Proust | Statement: [Lydia Davis, notableAuthorTranslated, Marcel Proust]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableAuthorTranslated Context triple: [Lydia Davis, notableAuthorTranslated, Marcel Proust]
-
A.
notableEnglishTranslator
Indicates that one entity is a notable translator who has translated works into English or is recognized for English translation.
-
B.
notableAuthorInLanguage
Indicates that a person is a particularly prominent or distinguished author who writes in the specified language.
-
C.
notableAuthorPublished
Indicates that a work was published by an author who is recognized as notable or distinguished.
-
D.
authorOfTranslation
chosen
Indicates that one entity is the person or agent who produced a translated version of a work originally created in another language.
-
E.
notableAuthorAttribute
Indicates that a particular attribute or characteristic is especially notable or significant for an author in the context of their work or recognition.
- 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_69e2fac350d08190b3affde1b451a8c5 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f6b2a65c7c8190ac40f1466ceadefc |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 18, 2026, 5:22 a.m.