Triple

T7690026
Position Surface form Disambiguated ID Type / Status
Subject Wallenberg family E174220 entity
Predicate ownsThrough P7585 FINISHED
Object FAM AB
FAM AB is a Swedish investment company that manages and develops long-term holdings on behalf of the Wallenberg family.
E681810 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: FAM AB | Statement: [Wallenberg family, ownsThrough, FAM AB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FAM AB
Context triple: [Wallenberg family, ownsThrough, FAM AB]
  • A. FAM
    FAM is the acronym commonly used to refer to the Mexican Air Force, the aerial warfare branch of Mexico’s armed forces.
  • B. FAMO
    FAMO was a German vehicle manufacturer best known for producing military half-tracks and armored vehicles for the Wehrmacht during World War II.
  • C. FAMa
    FAMa is the national military force of Mali responsible for the country’s defense and security operations.
  • D. FAMET
    FAMET is the Spanish Army’s aviation branch responsible for operating and supporting its helicopter and air mobility units.
  • E. F.A.C.
    F.A.C. is the standard legal abbreviation used to refer to the Florida Administrative Code, which contains the administrative rules and regulations of the state of Florida.
  • 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: FAM AB
Triple: [Wallenberg family, ownsThrough, FAM AB]
Generated description
FAM AB is a Swedish investment company that manages and develops long-term holdings on behalf of the Wallenberg family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: FAM AB
Target entity description: FAM AB is a Swedish investment company that manages and develops long-term holdings on behalf of the Wallenberg family.
  • A. FAM
    FAM is the acronym commonly used to refer to the Mexican Air Force, the aerial warfare branch of Mexico’s armed forces.
  • B. FAMO
    FAMO was a German vehicle manufacturer best known for producing military half-tracks and armored vehicles for the Wehrmacht during World War II.
  • C. FAMa
    FAMa is the national military force of Mali responsible for the country’s defense and security operations.
  • D. FAMET
    FAMET is the Spanish Army’s aviation branch responsible for operating and supporting its helicopter and air mobility units.
  • E. F.A.C.
    F.A.C. is the standard legal abbreviation used to refer to the Florida Administrative Code, which contains the administrative rules and regulations of the state of Florida.
  • 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_69c6995966348190939e6c37ba272c06 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702421dec8190a74f8ade992ca811 completed March 27, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a26686a08190acf66586f6c7592b completed March 29, 2026, 3:54 a.m.
NEDg Description generation batch_69c8a34c93a081908ec3509c3abb3866 completed March 29, 2026, 3:58 a.m.
NED2 Entity disambiguation (via description) batch_69c8a3b4e0a88190ad525c83bd03e09f completed March 29, 2026, 3:59 a.m.
Created at: March 27, 2026, 4:02 p.m.