Triple

T3404348
Position Surface form Disambiguated ID Type / Status
Subject Angers E71733 entity
Predicate historicalName P65 FINISHED
Object Andegavum
Andegavum is the Latin name for the French city of Angers, historically used in Roman and medieval sources.
 E355208 NE FINISHED

How this triple was built (4 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: Andegavum | Statement: [Angers, historicalName, Andegavum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Andegavum
Context triple: [Angers, historicalName, Andegavum]
  • A. Avgad
    Avgad is a variant form or textual tradition associated with the Jewish mystical work Temurah.
  • B. Afantou
    Afantou is a village and seaside resort on the island of Rhodes in Greece, known for its long beach and traditional character.
  • C. Ovilava
    Ovilava was a major Roman-era city in the province of Noricum, located at the site of modern Wels in present-day Austria.
  • D. Vallentuna
    Vallentuna is a locality in Stockholm County, Sweden, known as a suburban community within the Stockholm metropolitan area.
  • E. Avarua
    Avarua is the main town and administrative, commercial, and cultural center of the Cook Islands, located on the north coast of Rarotonga.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Andegavum
Triple: [Angers, historicalName, Andegavum]
Generated description
Andegavum is the Latin name for the French city of Angers, historically used in Roman and medieval sources.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Andegavum
Target entity description: Andegavum is the Latin name for the French city of Angers, historically used in Roman and medieval sources.
  • A. Avgad
    Avgad is a variant form or textual tradition associated with the Jewish mystical work Temurah.
  • B. Afantou
    Afantou is a village and seaside resort on the island of Rhodes in Greece, known for its long beach and traditional character.
  • C. Ovilava
    Ovilava was a major Roman-era city in the province of Noricum, located at the site of modern Wels in present-day Austria.
  • D. Vallentuna
    Vallentuna is a locality in Stockholm County, Sweden, known as a suburban community within the Stockholm metropolitan area.
  • E. Avarua
    Avarua is the main town and administrative, commercial, and cultural center of the Cook Islands, located on the north coast of Rarotonga.
  • F. None of above. chosen

Provenance (5 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_69ad85aac4808190a092c9cc8911f584 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb8e8ea848190b4ac167f1aba8ebd completed March 8, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bd69f388190981da6454dfd4fb1 completed March 12, 2026, 11:27 p.m.
NEDg Description generation batch_69b34e486c3c81908e73c5b75baf119c completed March 12, 2026, 11:37 p.m.
NED2 Entity disambiguation (via description) batch_69b34fc420b08190baee678721b1b32c completed March 12, 2026, 11:44 p.m.
Created at: March 8, 2026, 3:14 p.m.