Triple
T8924640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Appian |
E212508
|
entity |
| Predicate | focusOfWork |
P65912
|
FINISHED |
| Object | history of the Roman Republic |
—
|
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: history of the Roman Republic | Statement: [Appian, focusOfWork, history of the Roman Republic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusOfWork Context triple: [Appian, focusOfWork, history of the Roman Republic]
-
A.
focusPosition
Indicates the spatial or logical position at which attention, concentration, or processing is currently directed within a given context.
-
B.
focusType
Indicates the specific kind or category of focus or attention that is being applied to or associated with an entity or interaction.
-
C.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
D.
focusModel
Indicates that one entity serves as the primary or central model that another entity is directed toward, based on, or concentrated on.
-
E.
canonicalFocus
chosen
Indicates that one entity is the primary or most representative focus or point of attention in relation to another entity.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66547de881909ea9bfd104b32893 |
completed | April 1, 2026, 12:27 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:57 p.m.