Triple

T2156724
Position Surface form Disambiguated ID Type / Status
Subject Arenig Fawr E47905 entity
Predicate overlooks P1323 FINISHED
Object Moel Llyfnant
Moel Llyfnant is a mountain in Snowdonia, Wales, known as a remote, grassy peak often climbed in conjunction with nearby Arenig Fawr.
E252047 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: Moel Llyfnant | Statement: [Arenig Fawr, overlooks, Moel Llyfnant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moel Llyfnant
Context triple: [Arenig Fawr, overlooks, Moel Llyfnant]
  • A. Moel Hebog
    Moel Hebog is a prominent mountain in North Wales known for its rugged slopes and panoramic views over the surrounding Snowdonia landscape.
  • B. Pen y Fan
    Pen y Fan is a prominent mountain in South Wales known for its sweeping views and popularity with hikers and outdoor enthusiasts.
  • C. Maerdy
    Maerdy is a former coal mining village located at the head of the Rhondda Fach valley in Rhondda Cynon Taf, South Wales.
  • D. Taf Fawr
    Taf Fawr is one of the principal headwater streams of the River Taff in South Wales, flowing through the Brecon Beacons before joining with other tributaries to form the main river.
  • E. Snowdon
    Snowdon is the tallest and most famous mountain in Wales, renowned for its scenic hiking routes and panoramic views.
  • 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: Moel Llyfnant
Triple: [Arenig Fawr, overlooks, Moel Llyfnant]
Generated description
Moel Llyfnant is a mountain in Snowdonia, Wales, known as a remote, grassy peak often climbed in conjunction with nearby Arenig Fawr.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Moel Llyfnant
Target entity description: Moel Llyfnant is a mountain in Snowdonia, Wales, known as a remote, grassy peak often climbed in conjunction with nearby Arenig Fawr.
  • A. Moel Hebog
    Moel Hebog is a prominent mountain in North Wales known for its rugged slopes and panoramic views over the surrounding Snowdonia landscape.
  • B. Pen y Fan
    Pen y Fan is a prominent mountain in South Wales known for its sweeping views and popularity with hikers and outdoor enthusiasts.
  • C. Maerdy
    Maerdy is a former coal mining village located at the head of the Rhondda Fach valley in Rhondda Cynon Taf, South Wales.
  • D. Taf Fawr
    Taf Fawr is one of the principal headwater streams of the River Taff in South Wales, flowing through the Brecon Beacons before joining with other tributaries to form the main river.
  • E. Snowdon
    Snowdon is the tallest and most famous mountain in Wales, renowned for its scenic hiking routes and panoramic views.
  • 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_69a88a1d1fd8819088b34990d69a712f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe67d6888190b8d3c07527c8f80e completed March 7, 2026, 5:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7ef2dda08190b55919f0df935a6d completed March 9, 2026, 8:04 a.m.
NEDg Description generation batch_69ae7f90d3a88190bf61c6f063b67c06 completed March 9, 2026, 8:06 a.m.
NED2 Entity disambiguation (via description) batch_69ae800868948190a5504969c4cabb7d completed March 9, 2026, 8:08 a.m.
Created at: March 4, 2026, 7:44 p.m.