Triple
T28411102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italica (renamed Corfinium) |
E719662
|
entity |
| Predicate | nearbyAncientPeoples |
P126418
|
FINISHED |
| Object | Marsi |
—
|
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: Marsi | Statement: [Italica (renamed Corfinium), nearbyAncientPeoples, Marsi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearbyAncientPeoples Context triple: [Italica (renamed Corfinium), nearbyAncientPeoples, Marsi]
-
A.
associatedAncientPeoples
Indicates a relationship where certain ancient peoples are historically or culturally linked or connected to a given entity.
-
B.
nearbyArchaeologicalCulture
Indicates that one archaeological culture is geographically close to another archaeological culture.
-
C.
nearAncientRegion
Indicates that one entity is located close to, or in the immediate vicinity of, a specified ancient geographical region.
-
D.
hasNearbyAncientCulture
chosen
Indicates that one entity is geographically close to another entity associated with an ancient culture or civilization.
-
E.
countryDuringAntiquity
Indicates that an entity functioned as a country or political territory specifically during the historical period of antiquity.
- 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_69eff6f0f37c8190b37bc6fab08a9449 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f7c29e1b848190b945c6c6120a5330 |
completed | May 3, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b6e7a881908deb96bedb2713f4 |
completed | May 3, 2026, 9:44 p.m. |
Created at: April 28, 2026, 1:27 a.m.