Triple

T20949458
Position Surface form Disambiguated ID Type / Status
Subject Loch na Keal E515939 entity
Predicate hasShoreSettlement P16159 FINISHED
Object Tiroran
Tiroran is a small coastal settlement on the Isle of Mull in Scotland, known for its scenic setting near Loch na Keal and its surrounding woodland and hillside landscapes.
 E1458762 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: Tiroran | Statement: [Loch na Keal, hasShoreSettlement, Tiroran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tiroran
Context triple: [Loch na Keal, hasShoreSettlement, Tiroran]
  • A. Termunten
    Termunten is a small village in the province of Groningen in the northeastern Netherlands, situated near the Ems estuary and the Wadden Sea.
  • B. Karrabin
    Karrabin is a rural-residential locality in the western outskirts of Ipswich, Queensland, Australia.
  • C. Armas
    Armas is a Finnish given name, notably used as one of the names of the renowned Finnish poet Eino Leino.
  • D. Orpo
    Orpo was the uniformed regular police force of Nazi Germany, responsible for maintaining public order and involved in numerous wartime atrocities and repressive activities.
  • E. Fussilat
    Fussilat is the 41st chapter of the Qur’an, known for its detailed exposition of divine revelation, signs in creation, and the consequences of accepting or rejecting the message.
  • 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: Tiroran
Triple: [Loch na Keal, hasShoreSettlement, Tiroran]
Generated description
Tiroran is a small coastal settlement on the Isle of Mull in Scotland, known for its scenic setting near Loch na Keal and its surrounding woodland and hillside landscapes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tiroran
Target entity description: Tiroran is a small coastal settlement on the Isle of Mull in Scotland, known for its scenic setting near Loch na Keal and its surrounding woodland and hillside landscapes.
  • A. Termunten
    Termunten is a small village in the province of Groningen in the northeastern Netherlands, situated near the Ems estuary and the Wadden Sea.
  • B. Karrabin
    Karrabin is a rural-residential locality in the western outskirts of Ipswich, Queensland, Australia.
  • C. Armas
    Armas is a Finnish given name, notably used as one of the names of the renowned Finnish poet Eino Leino.
  • D. Orpo
    Orpo was the uniformed regular police force of Nazi Germany, responsible for maintaining public order and involved in numerous wartime atrocities and repressive activities.
  • E. Fussilat
    Fussilat is the 41st chapter of the Qur’an, known for its detailed exposition of divine revelation, signs in creation, and the consequences of accepting or rejecting the message.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadc08148190b4ff710f94462a26 completed April 21, 2026, 4:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09278e12888190bbf727d1d8f90a4f completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a092819af008190bc51cd6367d7542a completed May 17, 2026, 2:29 a.m.
NED2 Entity disambiguation (via description) batch_6a092896b75881909d5145ccaef0cd7e completed May 17, 2026, 2:31 a.m.
Created at: April 16, 2026, 1:15 p.m.