Triple
T14179106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eparchius |
E351406
|
entity |
| Predicate | bearerHeldTitle |
P93996
|
FINISHED |
| Object | Roman emperor |
—
|
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: Roman emperor | Statement: [Eparchius, bearerHeldTitle, Roman emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bearerHeldTitle Context triple: [Eparchius, bearerHeldTitle, Roman emperor]
-
A.
bearerTitle
chosen
Indicates that one entity holds or is designated by a specific formal title associated with a role, rank, or position.
-
B.
bearerFounded
Indicates that the bearer (such as a person or organization) is the one who established or created the associated entity (such as a company, institution, or project).
-
C.
heldTitleOver
Indicates that one entity possessed and maintained a particular title, rank, or designation in relation to another entity for a period of time.
-
D.
titleHeldAs
Indicates that an entity holds or possesses a specific title in a particular capacity or role.
-
E.
heldTitleUntil
Indicates that an entity possessed or held a specific title or position continuously up to a particular end date or point in time.
- 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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61c90abc8190a9b9dc1f50db59fa |
completed | April 14, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69de05baed64819096590e5618a3a8ed |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:02 a.m.