Triple

T31139344
Position Surface form Disambiguated ID Type / Status
Subject Armoy E793737 entity
Predicate hasCulturalEvent P2955 FINISHED
Object Armoy Road Races
Armoy Road Races is a prominent Irish national road racing motorcycle event held on closed public roads near the village of Armoy in Northern Ireland.
E1946977 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: Armoy Road Races | Statement: [Armoy, hasCulturalEvent, Armoy Road Races]
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: Armoy Road Races
Triple: [Armoy, hasCulturalEvent, Armoy Road Races]
Generated description
Armoy Road Races is a prominent Irish national road racing motorcycle event held on closed public roads near the village of Armoy in Northern Ireland.

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_69f224d2b3a48190aa9dd26fbf6eab1a completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f69793f8748190a6e785fc2c307a59 completed May 3, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2938cda8908190b8258e85fff70779 completed June 10, 2026, 10:13 a.m.
NEDg Description generation batch_6a2939db5768819087ecea8a785c637d completed June 10, 2026, 10:18 a.m.
NED2 Entity disambiguation (via description) batch_6a293bf644548190beb05576e2c10d29 completed June 10, 2026, 10:27 a.m.
Created at: April 29, 2026, 9:05 p.m.