Triple

T8514525
Position Surface form Disambiguated ID Type / Status
Subject Lychnidus E201538 entity
Predicate connectedTo P37 FINISHED
Object Dyrrachium E197621 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: Dyrrachium | Statement: [Lychnidus, connectedTo, Dyrrachium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dyrrachium
Context triple: [Lychnidus, connectedTo, Dyrrachium]
  • A. Dyrrhachium chosen
    Dyrrhachium was an important ancient Greek and later Roman port city on the Adriatic coast, in the area of modern-day Durrës, Albania.
  • B. Ambracia
    Ambracia was an ancient Greek city in Epirus that became an important regional center and later the capital of King Pyrrhus.
  • C. Taurisium
    Taurisium is an ancient fortified settlement in present-day North Macedonia, traditionally regarded as the birthplace of the Byzantine emperor Justinian I.
  • D. Epidamnos
    Epidamnos was an ancient Greek colony on the Adriatic coast, located where the modern Albanian city of Durrës now stands.
  • E. Samarobriva
    Samarobriva is the ancient Roman name for the city now known as Amiens in northern France, which served as an important settlement in Roman Gaul.
  • 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_69ca8320e5748190ac2c585a0bba8193 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe60e12848190a4a3dfa457aef275 completed March 31, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4e56ef088190b4f938486bbb7962 completed April 2, 2026, 11:09 a.m.
Created at: March 30, 2026, 6:15 p.m.