Triple

T18611
Position Surface form Disambiguated ID Type / Status
Subject Scottish Gaelic E367 entity
Predicate derivedFrom P909 FINISHED
Object Old Irish
Old Irish is the earliest recorded form of the Goidelic Celtic languages, historically spoken in Ireland and parts of Scotland between roughly the 6th and 10th centuries.
 E1286 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: Old Irish | Statement: [Scottish Gaelic, derivedFrom, Old Irish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Old Irish
Context triple: [Scottish Gaelic, derivedFrom, Old Irish]
  • A. Scottish Gaelic
    Scottish Gaelic is a Celtic language native to Scotland, historically spoken in the Highlands and Islands and closely related to Irish and Manx.
  • B. Norman
    Norman is a masculine given name of English origin that became widely used in the English-speaking world.
  • C. Veritas
    Veritas is the Latin word for "truth" and is famously used as the motto of Harvard University.
  • D. English
    English is a widely spoken West Germanic language that serves as a global lingua franca in education, business, science, and international communication.
  • E. Trinity
    The Trinity is the central Christian doctrine that God exists as one divine being in three distinct, co-equal persons: the Father, the Son, and the Holy Spirit.
  • 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: Old Irish
Triple: [Scottish Gaelic, derivedFrom, Old Irish]
Generated description
Old Irish is the earliest recorded form of the Goidelic Celtic languages, historically spoken in Ireland and parts of Scotland between roughly the 6th and 10th centuries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Old Irish
Target entity description: Old Irish is the earliest recorded form of the Goidelic Celtic languages, historically spoken in Ireland and parts of Scotland between roughly the 6th and 10th centuries.
  • A. Scottish Gaelic
    Scottish Gaelic is a Celtic language native to Scotland, historically spoken in the Highlands and Islands and closely related to Irish and Manx.
  • B. Norman
    Norman is a masculine given name of English origin that became widely used in the English-speaking world.
  • C. Veritas
    Veritas is the Latin word for "truth" and is famously used as the motto of Harvard University.
  • D. English
    English is a widely spoken West Germanic language that serves as a global lingua franca in education, business, science, and international communication.
  • E. Trinity
    The Trinity is the central Christian doctrine that God exists as one divine being in three distinct, co-equal persons: the Father, the Son, and the Holy Spirit.
  • 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_69a240778d288190815c0052ebbbcc91 completed Feb. 28, 2026, 1:10 a.m.
NER Named-entity recognition batch_69a2465d9038819087f875a5afac9541 completed Feb. 28, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69a248e73c6c8190a83d10709aa3f9c7 completed Feb. 28, 2026, 1:46 a.m.
NEDg Description generation batch_69a249cbc63881908a99d2f82270b96b completed Feb. 28, 2026, 1:50 a.m.
NED2 Entity disambiguation (via description) batch_69a24a54686c819088cfe99468b2c693 completed Feb. 28, 2026, 1:52 a.m.
Created at: Feb. 28, 2026, 1:14 a.m.