Triple
T35782066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ankara inscription |
E1034463
|
entity |
| Predicate | authorOfTextInscribed |
P191977
|
FINISHED |
| Object | Augustus |
—
|
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: Augustus | Statement: [Ankara inscription, authorOfTextInscribed, Augustus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorOfTextInscribed Context triple: [Ankara inscription, authorOfTextInscribed, Augustus]
-
A.
sculptorInscription
Indicates that an inscription identifies the sculptor responsible for creating a particular sculpture or artwork.
-
B.
firstInscribedBy
Indicates that an object (such as a text, symbol, or inscription) was originally inscribed or written for the first time by a particular agent.
-
C.
authorAccordingToText
chosen
Indicates that a specified entity is identified as the author of a work according to the information given in a particular text source.
-
D.
hasNameInscribed
Indicates that an entity bears another entity’s name physically inscribed on its surface.
-
E.
authorDescribedIn
Indicates that information about an author is provided or discussed within a particular document or source.
- 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_69f76e14a1e081908eddd57bd6fdb3be |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe0d165a48819098b854318a50d76c |
completed | May 8, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69fe0931002481908a95b34f95e9f64e |
completed | May 8, 2026, 4:02 p.m. |
Created at: May 3, 2026, 4:06 p.m.