Triple

T11129577
Position Surface form Disambiguated ID Type / Status
Subject Tarsos E263240 entity
Predicate hasHistoricalName P2834 FINISHED
Object Tarsos E263240 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: Tarsos | Statement: [Tarsos, hasHistoricalName, Tarsos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarsos
Context triple: [Tarsos, hasHistoricalName, Tarsos]
  • A. Tarsos chosen
    Tarsos is the ancient name of the historic city of Tarsus in Cilicia, a significant cultural and commercial center in the eastern Mediterranean world.
  • B. Tyndis
    Tyndis was an important ancient port city on the Malabar Coast of South India, serving as a key hub in Indian Ocean trade networks under the Chera dynasty.
  • C. Balasinor
    Balasinor is a town in Gujarat, India, known for its nearby dinosaur fossil park and rich paleontological significance.
  • D. Thasus
    Thasus is a minor figure in Greek mythology, traditionally regarded as a son of the Phoenician king Agenor and associated with the island of Thasos.
  • E. Kamorta
    Kamorta is a significant inhabited island and settlement in India’s Nicobar archipelago, known for its strategic location and indigenous Nicobarese communities.
  • 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_69d6aa9c0ba08190bbd19c217489b755 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e830e804819097fcc3826d84dab8 completed April 9, 2026, 5:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69e441dcb4608190a4cfa46c194d11ae completed April 19, 2026, 2:45 a.m.
Created at: April 8, 2026, 9:28 p.m.