Triple
T24231571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Megasthenes |
E601747
|
entity |
| Predicate | workSurvivesAs |
P28056
|
FINISHED |
| Object | fragments in later authors |
—
|
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: fragments in later authors | Statement: [Megasthenes, workSurvivesAs, fragments in later authors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workSurvivesAs Context triple: [Megasthenes, workSurvivesAs, fragments in later authors]
-
A.
survivingWorkForm
chosen
Indicates that one work is a surviving or extant form/version of another, typically when the original or earlier form is lost or no longer available.
-
B.
survivesAs
Indicates that one entity continues to exist or persist in place of, or after the end or transformation of, another entity.
-
C.
survivesWith
Indicates that one entity continues to live, endure, or remain viable in the presence, context, or company of another entity.
-
D.
worksAs
Indicates that an entity performs the role, job, or occupation specified by another entity.
-
E.
extentOfSurvivalOfWork
Indicates the degree to which a work has been preserved or remains extant.
- 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_69e29538aafc8190a2386fdebbd1393b |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f287e3de908190917a5bf66d9df5c9 |
completed | April 29, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:01 a.m.