Triple

T7957776
Position Surface form Disambiguated ID Type / Status
Subject Achaia E184782 entity
Predicate visitedBy P1096 FINISHED
Object Apollos
Apollos was an eloquent Jewish Christian teacher and missionary in the early church, known from the New Testament for his preaching and leadership in cities such as Corinth.
 E704651 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: Apollos | Statement: [Achaia, visitedBy, Apollos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Apollos
Context triple: [Achaia, visitedBy, Apollos]
  • A. Cleopas
    Cleopas is a figure from the New Testament, known as one of the disciples who encountered the risen Jesus on the road to Emmaus.
  • B. Apollos Smith
    Apollos Smith was a 19th-century landowner and developer whose influence in the Adirondack region led to the naming of the hamlet of Paul Smiths, New York, in his honor.
  • C. Stephanos
    Stephanos is the Greek form of the name Stephen, traditionally associated with Saint Stephen, the first Christian martyr.
  • D. Hymenaeus
    Hymenaeus is a minor Greek god associated with marriage ceremonies, often invoked in wedding songs and processions.
  • E. Aristo
    Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
  • 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: Apollos
Triple: [Achaia, visitedBy, Apollos]
Generated description
Apollos was an eloquent Jewish Christian teacher and missionary in the early church, known from the New Testament for his preaching and leadership in cities such as Corinth.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Apollos
Target entity description: Apollos was an eloquent Jewish Christian teacher and missionary in the early church, known from the New Testament for his preaching and leadership in cities such as Corinth.
  • A. Cleopas
    Cleopas is a figure from the New Testament, known as one of the disciples who encountered the risen Jesus on the road to Emmaus.
  • B. Apollos Smith
    Apollos Smith was a 19th-century landowner and developer whose influence in the Adirondack region led to the naming of the hamlet of Paul Smiths, New York, in his honor.
  • C. Stephanos
    Stephanos is the Greek form of the name Stephen, traditionally associated with Saint Stephen, the first Christian martyr.
  • D. Hymenaeus
    Hymenaeus is a minor Greek god associated with marriage ceremonies, often invoked in wedding songs and processions.
  • E. Aristo
    Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
  • 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_69ca8293a2388190aace944d7ed9c0c0 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3b7ebb24819094bc011d51ef63fb completed March 31, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe072ef4c8190a8e078c5280913db completed March 31, 2026, 2:55 p.m.
NEDg Description generation batch_69cc46c11e68819087f5083bb85ec7ab completed March 31, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69cc47fa1524819089ef5b3f8bf7f670 completed March 31, 2026, 10:17 p.m.
Created at: March 30, 2026, 5:11 p.m.