Triple

T14488025
Position Surface form Disambiguated ID Type / Status
Subject LaserLight E359287 entity
Predicate songwriter P1141 FINISHED
Object Karl-Michael
Karl-Michael is a songwriter known for his work on the song "LaserLight."
E1102349 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: Karl-Michael | Statement: [LaserLight, songwriter, Karl-Michael]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl-Michael
Context triple: [LaserLight, songwriter, Karl-Michael]
  • A. Karl Martin
    Karl Martin is a fictional character from the television series "Lost," portrayed as a young member of the Others who becomes involved in several key storylines on the island.
  • B. Karl-Wilhelm
    Karl-Wilhelm is the given name of Karl-Wilhelm von Schlieben, a German general who served in the Wehrmacht during World War II.
  • C. Johan Karlberg
    Johan Karlberg is a Swedish musician best known as a member of the folk group Hootenanny Singers.
  • D. Mikael Lindfelt
    Mikael Lindfelt is a Finnish academic who serves as the rector (president) of Åbo Akademi University, a Swedish-language university in Finland.
  • E. Karl
    Karl is the given first name of Charles Proteus Steinmetz, the renowned German-American mathematician and electrical engineer who revolutionized the understanding of alternating current systems.
  • 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: Karl-Michael
Triple: [LaserLight, songwriter, Karl-Michael]
Generated description
Karl-Michael is a songwriter known for his work on the song "LaserLight."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karl-Michael
Target entity description: Karl-Michael is a songwriter known for his work on the song "LaserLight."
  • A. Karl Martin
    Karl Martin is a fictional character from the television series "Lost," portrayed as a young member of the Others who becomes involved in several key storylines on the island.
  • B. Karl-Wilhelm
    Karl-Wilhelm is the given name of Karl-Wilhelm von Schlieben, a German general who served in the Wehrmacht during World War II.
  • C. Johan Karlberg
    Johan Karlberg is a Swedish musician best known as a member of the folk group Hootenanny Singers.
  • D. Mikael Lindfelt
    Mikael Lindfelt is a Finnish academic who serves as the rector (president) of Åbo Akademi University, a Swedish-language university in Finland.
  • E. Karl
    Karl is the given first name of Charles Proteus Steinmetz, the renowned German-American mathematician and electrical engineer who revolutionized the understanding of alternating current systems.
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de930bd1d48190abd6c47da0a3ebc8 completed April 14, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d8f1bf081908c37f8f41767b382 completed May 8, 2026, 4:58 a.m.
NEDg Description generation batch_69fd6faa43808190a9fe934f8f472a61 completed May 8, 2026, 5:07 a.m.
NED2 Entity disambiguation (via description) batch_69fd700572e48190aa9bbb544a25796e completed May 8, 2026, 5:09 a.m.
Created at: April 10, 2026, 1:20 a.m.