Triple

T4799541
Position Surface form Disambiguated ID Type / Status
Subject Roman Syria E106798 entity
Predicate capital P234 FINISHED
Object Antioch E26797 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: Antioch | Statement: [Roman Syria, capital, Antioch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Antioch
Context triple: [Roman Syria, capital, Antioch]
  • A. Antioch chosen
    Antioch was an important ancient city in Syria that became a major center of early Christianity and missionary activity.
  • B. Antioch, California
    Antioch, California is a historic city in the East Bay region of the San Francisco Bay Area known for its suburban communities along the Sacramento–San Joaquin River Delta.
  • C. Alexandria
    Alexandria is a small town in West Dunbartonshire, Scotland, situated near the southern end of Loch Lomond and known as a gateway to the Loch Lomond and The Trossachs National Park.
  • D. Alexandria
    Alexandria is a mid-sized city in central Louisiana known as a regional hub for government, healthcare, and commerce along the Red River.
  • E. Alexandria
    Alexandria is a historic Mediterranean port city in northern Egypt, renowned for its ancient library, lighthouse, and enduring role as a cultural and intellectual center.
  • 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_69bd43f6a1e08190bf0a372bfc336ee5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd663512d0819099064903613108d9 completed March 20, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43fc9e448190b9bfd2ff59ab4146 completed March 21, 2026, 7:08 a.m.
Created at: March 20, 2026, 1:23 p.m.