Triple

T30493205
Position Surface form Disambiguated ID Type / Status
Subject Cruden Bay E775925 entity
Predicate hasHarbour P3007 FINISHED
Object Port Erroll harbour
Port Erroll harbour is a small historic fishing harbour that serves the coastal village of Cruden Bay in Aberdeenshire, Scotland.
E1918278 NE FINISHED

How this triple was built (2 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: Port Erroll harbour | Statement: [Cruden Bay, hasHarbour, Port Erroll harbour]
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: Port Erroll harbour
Triple: [Cruden Bay, hasHarbour, Port Erroll harbour]
Generated description
Port Erroll harbour is a small historic fishing harbour that serves the coastal village of Cruden Bay in Aberdeenshire, Scotland.

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_69f22498c5d481908aaea89e6fab8280 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f68775ebd081908706784fe8f8fdf8 completed May 2, 2026, 11:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a27ac2ea8b08190a0acf2657525c301 completed June 9, 2026, 6:01 a.m.
NEDg Description generation batch_6a27acef0d7481908899cea092a71c89 completed June 9, 2026, 6:04 a.m.
NED2 Entity disambiguation (via description) batch_6a27b605cb7081908d5e7d9110812466 completed June 9, 2026, 6:43 a.m.
Created at: April 29, 2026, 8:14 p.m.