Triple
T3160237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ancient Italy |
E66083
|
entity |
| Predicate | majorCity |
P316
|
FINISHED |
| Object | Tarentum |
E51791
|
NE 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: Tarentum | Statement: [ancient Italy, majorCity, Tarentum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tarentum Context triple: [ancient Italy, majorCity, Tarentum]
-
A.
Tarentum
chosen
Tarentum was an important ancient Greek colony in southern Italy, known for its strategic harbor, economic prosperity, and cultural influence in the region of Magna Graecia.
-
B.
Iconium
Iconium was an ancient city in central Anatolia, historically significant as a Hellenistic, Roman, and early Christian center, located in what is now Konya, Turkey.
-
C.
Semyorka
Semyorka is the nickname for the Soviet R-7 family of rockets, historically significant as the launch vehicles for Sputnik and early crewed spaceflights.
-
D.
Diggstown
Diggstown is a 1992 sports comedy-drama film centered on a high-stakes boxing con set in a small Southern town.
-
E.
Albanopolis
Albanopolis is a historically obscure city or town, traditionally identified in Christian tradition as the place where the Apostle Bartholomew was martyred.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada61606bc8190a8ad760d680924eb |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2250d2b8c81908585d9563f9b4d16 |
completed | March 12, 2026, 2:29 a.m. |
Created at: March 8, 2026, 3:05 p.m.