Triple

T4939479
Position Surface form Disambiguated ID Type / Status
Subject Langres E110891 entity
Predicate wasRomanName P6662 FINISHED
Object Andematunnum
Andematunnum was the ancient Roman-era settlement that later became the French town of Langres, an important center in northeastern Gaul.
 E481407 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: Andematunnum | Statement: [Langres, wasRomanName, Andematunnum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Andematunnum
Context triple: [Langres, wasRomanName, Andematunnum]
  • A. Taphus
    Taphus was the original name of the town that later became Charlotte Amalie, the capital of the U.S. Virgin Islands.
  • B. Nemocón
    Nemocón is a Colombian town in the department of Cundinamarca, best known for its historic underground salt mine and scenic Andean surroundings.
  • C. Amarah
    Amarah is a city in southeastern Iraq situated along the Tigris River and serving as the capital of Maysan Governorate.
  • D. Eminado
    Eminado is a popular Afrobeat song by Nigerian singer Tiwa Savage, known for its catchy melody and romantic lyrics.
  • E. Afantou
    Afantou is a village and seaside resort on the island of Rhodes in Greece, known for its long beach and traditional character.
  • 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: Andematunnum
Triple: [Langres, wasRomanName, Andematunnum]
Generated description
Andematunnum was the ancient Roman-era settlement that later became the French town of Langres, an important center in northeastern Gaul.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Andematunnum
Target entity description: Andematunnum was the ancient Roman-era settlement that later became the French town of Langres, an important center in northeastern Gaul.
  • A. Taphus
    Taphus was the original name of the town that later became Charlotte Amalie, the capital of the U.S. Virgin Islands.
  • B. Nemocón
    Nemocón is a Colombian town in the department of Cundinamarca, best known for its historic underground salt mine and scenic Andean surroundings.
  • C. Amarah
    Amarah is a city in southeastern Iraq situated along the Tigris River and serving as the capital of Maysan Governorate.
  • D. Eminado
    Eminado is a popular Afrobeat song by Nigerian singer Tiwa Savage, known for its catchy melody and romantic lyrics.
  • E. Afantou
    Afantou is a village and seaside resort on the island of Rhodes in Greece, known for its long beach and traditional character.
  • 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_69bd4415eee08190bdce70276e56a5b4 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7088f6e48190bf09e58ab053a4d1 completed March 20, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77bf1f0481909cd007c78096f7c5 completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be7868a9148190b9f165fb2406dd9d completed March 21, 2026, 10:52 a.m.
NED2 Entity disambiguation (via description) batch_69be7916ff888190ba62e65b6422633c completed March 21, 2026, 10:55 a.m.
Created at: March 20, 2026, 1:31 p.m.