Triple

T5932706
Position Surface form Disambiguated ID Type / Status
Subject Via Agrippa E131973 entity
Predicate connects P390 FINISHED
Object Arelate
Arelate, known today as Arles in southern France, was an important Roman city and regional hub in the province of Gallia Narbonensis.
E133561 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: Arelate | Statement: [Via Agrippa, connects, Arelate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arelate
Context triple: [Via Agrippa, connects, Arelate]
  • A. Arke
    Arke was a Dutch leisure airline and tour operator brand that later became part of TUI and was rebranded as TUI fly Netherlands.
  • B. Arekuna
    Arekuna are an Indigenous people of the Guiana Highlands region in northern South America, culturally and linguistically related to other Cariban-speaking groups.
  • C. Aparan
    Aparan is a small town in Armenia’s Aragatsotn Province, known for its proximity to Mount Aragats and its historic churches and monuments.
  • D. Aru
    Aru is a town in the northeastern Democratic Republic of the Congo, near the Ugandan border, serving as a local administrative and trading center in Ituri Province.
  • E. Antu
    Antu is one of the four 8.2-meter Unit Telescopes of the Very Large Telescope array operated by the European Southern Observatory at Paranal in Chile.
  • 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: Arelate
Triple: [Via Agrippa, connects, Arelate]
Generated description
Arelate, known today as Arles in southern France, was an important Roman city and regional hub in the province of Gallia Narbonensis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Arelate
Target entity description: Arelate, known today as Arles in southern France, was an important Roman city and regional hub in the province of Gallia Narbonensis.
  • A. Arelate chosen
    Arelate was an important ancient Roman city in southern Gaul, known today as Arles in modern France.
  • B. Arke
    Arke was a Dutch leisure airline and tour operator brand that later became part of TUI and was rebranded as TUI fly Netherlands.
  • C. Arekuna
    Arekuna are an Indigenous people of the Guiana Highlands region in northern South America, culturally and linguistically related to other Cariban-speaking groups.
  • D. Aparan
    Aparan is a small town in Armenia’s Aragatsotn Province, known for its proximity to Mount Aragats and its historic churches and monuments.
  • E. Aru
    Aru is a town in the northeastern Democratic Republic of the Congo, near the Ugandan border, serving as a local administrative and trading center in Ituri Province.
  • F. None of above.

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_69c0085b75e88190a632f9691f9da48b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0389df18c81909027a9db7596f0c1 completed March 22, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0c064d2a4819096085668182cfde1 completed March 23, 2026, 4:24 a.m.
NEDg Description generation batch_69c0c109b3288190928dc4539a2872c2 completed March 23, 2026, 4:26 a.m.
NED2 Entity disambiguation (via description) batch_69c0c1f6fe60819080a00976740b6a9c completed March 23, 2026, 4:30 a.m.
Created at: March 22, 2026, 4 p.m.