Triple

T20836938
Position Surface form Disambiguated ID Type / Status
Subject Harald Grenske E512983 entity
Predicate grandfather P979 FINISHED
Object Björn Farmann
Björn Farmann was a 10th-century Norwegian petty king and son of Harald Fairhair, known from early Norse historical tradition.
E1453625 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: Björn Farmann | Statement: [Harald Grenske, grandfather, Björn Farmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Björn Farmann
Context triple: [Harald Grenske, grandfather, Björn Farmann]
  • A. Björn Erlendsson
    Björn Erlendsson is a person known primarily through genealogical records as the brother of Margret Erlendsdatter.
  • B. Kjartan Sveinsson
    Kjartan Sveinsson is an Icelandic multi-instrumentalist and composer best known as the longtime keyboardist and arranger for the post-rock band Sigur Rós.
  • C. Sveinn Björnsson
    Sveinn Björnsson was an Icelandic politician and diplomat who became the country's first president following its independence from Denmark.
  • D. Bragi Ólafsson
    Bragi Ólafsson is an Icelandic musician and writer best known as the bassist of the alternative rock band The Sugarcubes.
  • E. Sveinbjörn Beinteinsson
    Sveinbjörn Beinteinsson was an Icelandic farmer, poet, and religious leader who played a key role in the modern revival of Norse paganism.
  • 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: Björn Farmann
Triple: [Harald Grenske, grandfather, Björn Farmann]
Generated description
Björn Farmann was a 10th-century Norwegian petty king and son of Harald Fairhair, known from early Norse historical tradition.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Björn Farmann
Target entity description: Björn Farmann was a 10th-century Norwegian petty king and son of Harald Fairhair, known from early Norse historical tradition.
  • A. Björn Erlendsson
    Björn Erlendsson is a person known primarily through genealogical records as the brother of Margret Erlendsdatter.
  • B. Kjartan Sveinsson
    Kjartan Sveinsson is an Icelandic multi-instrumentalist and composer best known as the longtime keyboardist and arranger for the post-rock band Sigur Rós.
  • C. Sveinn Björnsson
    Sveinn Björnsson was an Icelandic politician and diplomat who became the country's first president following its independence from Denmark.
  • D. Bragi Ólafsson
    Bragi Ólafsson is an Icelandic musician and writer best known as the bassist of the alternative rock band The Sugarcubes.
  • E. Sveinbjörn Beinteinsson
    Sveinbjörn Beinteinsson was an Icelandic farmer, poet, and religious leader who played a key role in the modern revival of Norse paganism.
  • 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_69e0b4cf62a88190bbf92351e9e57259 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3280a1881909a86d1fe498aee50 completed April 21, 2026, 12:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a090afd181c81909dba7617c286af58 completed May 17, 2026, 12:25 a.m.
NEDg Description generation batch_6a090c524a308190bb063e0f5200cef7 completed May 17, 2026, 12:31 a.m.
NED2 Entity disambiguation (via description) batch_6a090cd6f0048190861b7a93560355aa completed May 17, 2026, 12:33 a.m.
Created at: April 16, 2026, 12:42 p.m.