Triple

T22446199
Position Surface form Disambiguated ID Type / Status
Subject Lars Bak E554868 entity
Predicate employer P7 FINISHED
Object OOVM
OOVM is a software company associated with Danish engineer Lars Bak, known for his work on high-performance virtual machines and programming language runtimes.
E1536600 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: OOVM | Statement: [Lars Bak, employer, OOVM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OOVM
Context triple: [Lars Bak, employer, OOVM]
  • A. OVSM
    OVSM is the volcanological and seismological observatory responsible for monitoring volcanic and earthquake activity in Martinique.
  • B. OMVS
    OMVS is the multinational organization responsible for managing and developing the shared water resources and infrastructure of the Senegal River basin.
  • C. OOA
    OOA is the IATA airport code for Oskaloosa Municipal Airport, a public airport serving Oskaloosa, Iowa, in the United States.
  • D. OVP
    OVP is the government office that supports and carries out the official duties and functions of the Vice President of the Philippines.
  • E. VOMM
    VOMM is the ICAO airport code for Chennai International Airport, a major aviation hub in southern India.
  • 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: OOVM
Triple: [Lars Bak, employer, OOVM]
Generated description
OOVM is a software company associated with Danish engineer Lars Bak, known for his work on high-performance virtual machines and programming language runtimes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: OOVM
Target entity description: OOVM is a software company associated with Danish engineer Lars Bak, known for his work on high-performance virtual machines and programming language runtimes.
  • A. OVSM
    OVSM is the volcanological and seismological observatory responsible for monitoring volcanic and earthquake activity in Martinique.
  • B. OMVS
    OMVS is the multinational organization responsible for managing and developing the shared water resources and infrastructure of the Senegal River basin.
  • C. OOA
    OOA is the IATA airport code for Oskaloosa Municipal Airport, a public airport serving Oskaloosa, Iowa, in the United States.
  • D. OVP
    OVP is the government office that supports and carries out the official duties and functions of the Vice President of the Philippines.
  • E. VOMM
    VOMM is the ICAO airport code for Chennai International Airport, a major aviation hub in southern India.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4803908190990280ebd258cb03 completed April 29, 2026, 1:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b0c7640fc8190a2dd1643a7c2a5b0 completed May 18, 2026, 12:56 p.m.
NEDg Description generation batch_6a0b0cd3f7bc8190bdc1e241ea1c642f completed May 18, 2026, 12:57 p.m.
NED2 Entity disambiguation (via description) batch_6a0b0d40e0c8819083a430e30dba1848 completed May 18, 2026, 12:59 p.m.
Created at: April 16, 2026, 8:47 p.m.