Triple
T1014876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homeric epics |
E21906
|
entity |
| Predicate | laterMedium |
P11606
|
FINISHED |
| Object | written manuscripts |
—
|
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: written manuscripts | Statement: [Homeric epics, laterMedium, written manuscripts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterMedium Context triple: [Homeric epics, laterMedium, written manuscripts]
-
A.
secondaryMedium
chosen
Indicates that an entity is associated with an additional, non-primary medium or channel through which it is expressed, delivered, or communicated.
-
B.
commonMedium
Indicates that two or more entities share the same medium or channel through which interaction, communication, or transmission occurs.
-
C.
primaryMedium
Indicates the main material, format, or channel through which something is created, expressed, or communicated.
-
D.
mediaWork
Indicates a relationship where one entity is a media-related work (such as a film, book, recording, or other creative media production) associated with another entity.
-
E.
writingMediumModern
Indicates that the writing activity is carried out using a modern medium or tool (such as digital or contemporary writing instruments) rather than traditional ones.
- 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_69a493c68e24819080ed0ee8bcfd5ce0 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7c05060819083c51717874074c8 |
completed | March 1, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69a4b7238d4c8190b22d6c2ac0ac4911 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.