Triple

T1702873
Position Surface form Disambiguated ID Type / Status
Subject Roman navy E36805 entity
Predicate garrisonedAt P28243 FINISHED
Object Carthage E22727 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: Carthage | Statement: [Roman navy, garrisonedAt, Carthage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carthage
Context triple: [Roman navy, garrisonedAt, Carthage]
  • A. Carthage chosen
    Carthage was an influential ancient Phoenician city-state and maritime empire in North Africa, renowned for its trade networks and conflicts with Rome during the Punic Wars.
  • B. Thugga
    Thugga is an ancient Roman-Berber city in modern-day Tunisia renowned for its well-preserved ruins and status as a UNESCO World Heritage Site.
  • C. Leptis Magna
    Leptis Magna is an exceptionally well-preserved ancient Roman city on the Mediterranean coast, renowned for its grand architecture and archaeological significance.
  • D. suffete of Carthage
    The suffete of Carthage was a chief magistrate and political leader in ancient Carthage, roughly comparable to a Roman consul.
  • E. Sabratha
    Sabratha is an ancient Phoenician and Roman city on Libya’s Mediterranean coast, renowned for its well-preserved classical ruins and monumental theater.
  • 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_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abaffad4748190995fec39bc8d7a1f completed March 7, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8acc65588190b09cc3528ff19653 completed March 8, 2026, 2:42 p.m.
Created at: March 4, 2026, 7:30 p.m.