Triple
T28527893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ennius’ lost tragedy Thyestes |
E721956
|
entity |
| Predicate | extentOfSurvival |
P75578
|
FINISHED |
| Object | survives only in fragments |
—
|
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: survives only in fragments | Statement: [Ennius’ lost tragedy Thyestes, extentOfSurvival, survives only in fragments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: extentOfSurvival Context triple: [Ennius’ lost tragedy Thyestes, extentOfSurvival, survives only in fragments]
-
A.
extentOfSurvivalOfWork
chosen
Indicates the degree to which a work has been preserved or remains extant.
-
B.
survivesFor
Indicates that one entity continues to exist, endure, or remain functional for a specified duration or period.
-
C.
averageSurvivalAfterDiagnosis
Indicates the typical length of time individuals survive following the point at which a condition or disease is first diagnosed.
-
D.
survivedDisease
Indicates that an entity successfully lived through and recovered from a specified disease.
-
E.
survivingFunction
Indicates that one entity continues to perform its role or maintain its operational capability after another related entity has failed, ended, or been removed.
- 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_69f01a5d7ec88190ada2d5be7c06c35d |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 3:26 a.m.