Triple

T7062452
Position Surface form Disambiguated ID Type / Status
Subject Cwmafan E164250 entity
Predicate locatedOnRiver P165 FINISHED
Object Afan
Afan is a river in South Wales that flows through industrial and former mining communities before reaching the sea at Port Talbot.
 E638973 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: Afan | Statement: [Cwmafan, locatedOnRiver, Afan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Afan
Context triple: [Cwmafan, locatedOnRiver, Afan]
  • A. Dawro
    Dawro is an Omotic language spoken primarily by the Dawro people in southwestern Ethiopia.
  • B. Moura
    Moura is a historic town in Portugal’s Alentejo region, known for its whitewashed architecture, olive oil production, and proximity to the Alqueva reservoir.
  • C. Moura
    Moura is a small coal-mining town in Central Queensland, Australia, known for its agricultural activities and history of mining disasters.
  • D. Nemyriv
    Nemyriv is a historic town in central Ukraine known for its Jewish heritage and role as a regional cultural and economic center.
  • E. Vishkanya
    Vishkanya is a 1991 Indian Hindi-language horror film known for its supernatural revenge plot and early appearance of actress Riya Sen.
  • 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: Afan
Triple: [Cwmafan, locatedOnRiver, Afan]
Generated description
Afan is a river in South Wales that flows through industrial and former mining communities before reaching the sea at Port Talbot.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Afan
Target entity description: Afan is a river in South Wales that flows through industrial and former mining communities before reaching the sea at Port Talbot.
  • A. Dawro
    Dawro is an Omotic language spoken primarily by the Dawro people in southwestern Ethiopia.
  • B. Moura
    Moura is a historic town in Portugal’s Alentejo region, known for its whitewashed architecture, olive oil production, and proximity to the Alqueva reservoir.
  • C. Moura
    Moura is a small coal-mining town in Central Queensland, Australia, known for its agricultural activities and history of mining disasters.
  • D. Nemyriv
    Nemyriv is a historic town in central Ukraine known for its Jewish heritage and role as a regional cultural and economic center.
  • E. Vishkanya
    Vishkanya is a 1991 Indian Hindi-language horror film known for its supernatural revenge plot and early appearance of actress Riya Sen.
  • 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_69c688796c148190adb2f1596f595f22 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e45b7488819094d2dd337731dab9 completed March 27, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c788b4b6788190aa4e74b9e7eb7eaa completed March 28, 2026, 7:52 a.m.
NEDg Description generation batch_69c7893f85588190b1ed983f00ea2532 completed March 28, 2026, 7:54 a.m.
NED2 Entity disambiguation (via description) batch_69c78b0fe83481909cad77ce740b81d5 completed March 28, 2026, 8:02 a.m.
Created at: March 27, 2026, 2:38 p.m.