Triple

T4914260
Position Surface form Disambiguated ID Type / Status
Subject Barnabas the Apostle E110308 entity
Predicate traveledTo P2694 FINISHED
Object Derbe
Derbe was an ancient city in the region of Lycaonia in Asia Minor, known from the New Testament as a place visited by Paul and his companions during their missionary journeys.
E478895 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: Derbe | Statement: [Barnabas the Apostle, traveledTo, Derbe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Derbe
Context triple: [Barnabas the Apostle, traveledTo, Derbe]
  • A. Eulachstadt
    Eulachstadt is a nickname for the Swiss city of Winterthur, reflecting its historical association with the Eulach River and its development as an important industrial and cultural center.
  • B. Andlau
    Andlau is a picturesque wine-growing village in northeastern France’s Alsace region, renowned for its historic abbey and surrounding vineyards.
  • C. Trebsen
    Trebsen is a small town in the Free State of Saxony in eastern Germany, known for its historic castle and location along the Mulde River.
  • D. Debar
    Debar is a small town in western North Macedonia known for its proximity to Mount Korab and the Macedonian–Albanian border.
  • E. Bogrod
    Bogrod is a goblin banker who works at Gringotts Wizarding Bank in the Harry Potter series.
  • 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: Derbe
Triple: [Barnabas the Apostle, traveledTo, Derbe]
Generated description
Derbe was an ancient city in the region of Lycaonia in Asia Minor, known from the New Testament as a place visited by Paul and his companions during their missionary journeys.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Derbe
Target entity description: Derbe was an ancient city in the region of Lycaonia in Asia Minor, known from the New Testament as a place visited by Paul and his companions during their missionary journeys.
  • A. Eulachstadt
    Eulachstadt is a nickname for the Swiss city of Winterthur, reflecting its historical association with the Eulach River and its development as an important industrial and cultural center.
  • B. Andlau
    Andlau is a picturesque wine-growing village in northeastern France’s Alsace region, renowned for its historic abbey and surrounding vineyards.
  • C. Trebsen
    Trebsen is a small town in the Free State of Saxony in eastern Germany, known for its historic castle and location along the Mulde River.
  • D. Debar
    Debar is a small town in western North Macedonia known for its proximity to Mount Korab and the Macedonian–Albanian border.
  • E. Bogrod
    Bogrod is a goblin banker who works at Gringotts Wizarding Bank in the Harry Potter series.
  • 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_69bd44132b94819088522d92beaadc78 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6e9f12b48190b3cb5378958d03cd completed March 20, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6feaf3dc81908b2c7a7409b1c952 completed March 21, 2026, 10:16 a.m.
NEDg Description generation batch_69be7147bff8819097059b1b24e2b0f7 completed March 21, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69be71d8dc6081908608d9e90498579b completed March 21, 2026, 10:24 a.m.
Created at: March 20, 2026, 1:29 p.m.