Triple

T10744648
Position Surface form Disambiguated ID Type / Status
Subject Taras E253418 entity
Predicate associatedCityState P25797 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: [Taras, associatedCityState, Tarentum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarentum
Context triple: [Taras, associatedCityState, 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. West Troy
    West Troy is the former name of Watervliet, a small industrial city located along the Hudson River in eastern New York State.
  • C. Pelasgus
    Pelasgus is a figure in Greek mythology often regarded as an ancestral or eponymous hero of the Pelasgians, a pre-Hellenic people of ancient Greece.
  • D. Shushtar
    Shushtar is a historic city in southwestern Iran, renowned for its ancient hydraulic system and rich cultural heritage.
  • E. Apollo, Pennsylvania
    Apollo, Pennsylvania is a small borough in Armstrong County known for its historic riverside setting along the Kiskiminetas River and its roots in western Pennsylvania’s early industrial development.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d711b6b4b48190bad08500fa963062 completed April 9, 2026, 2:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69e343ffc428819085599f251b7553e5 completed April 18, 2026, 8:42 a.m.
Created at: April 8, 2026, 9:15 p.m.