Triple

T2313718
Position Surface form Disambiguated ID Type / Status
Subject Harald Welte E51014 entity
Predicate notableWork P4 FINISHED
Object osmo-pcu
osmo-pcu is an open-source GSM/GPRS packet control unit software project, best known as part of the Osmocom mobile communications stack initiated by Harald Welte.
E255521 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: osmo-pcu | Statement: [Harald Welte, notableWork, osmo-pcu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: osmo-pcu
Context triple: [Harald Welte, notableWork, osmo-pcu]
  • A. OVS
    OVS is the New York State agency that provides financial assistance, advocacy, and support services to victims of crime.
  • B. Orbis OS
    Orbis OS is Sony's customized operating system for the PlayStation 4, built on a modified version of FreeBSD to power the console's gaming and multimedia features.
  • C. OSCT
    OSCT is the acronym for the UK government’s Office for Security and Counter-Terrorism, which leads national strategy and policy on counter-terrorism and security.
  • D. OS/VS1
    OS/VS1 is an IBM mainframe operating system from the 1970s designed for single-virtual-storage environments on System/370 hardware.
  • E. OSSE
    OSSE is the District of Columbia’s state education agency responsible for overseeing public education policies, programs, and accountability across the city.
  • 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: osmo-pcu
Triple: [Harald Welte, notableWork, osmo-pcu]
Generated description
osmo-pcu is an open-source GSM/GPRS packet control unit software project, best known as part of the Osmocom mobile communications stack initiated by Harald Welte.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: osmo-pcu
Target entity description: osmo-pcu is an open-source GSM/GPRS packet control unit software project, best known as part of the Osmocom mobile communications stack initiated by Harald Welte.
  • A. OVS
    OVS is the New York State agency that provides financial assistance, advocacy, and support services to victims of crime.
  • B. Orbis OS
    Orbis OS is Sony's customized operating system for the PlayStation 4, built on a modified version of FreeBSD to power the console's gaming and multimedia features.
  • C. OSCT
    OSCT is the acronym for the UK government’s Office for Security and Counter-Terrorism, which leads national strategy and policy on counter-terrorism and security.
  • D. OS/VS1
    OS/VS1 is an IBM mainframe operating system from the 1970s designed for single-virtual-storage environments on System/370 hardware.
  • E. OSSE
    OSSE is the District of Columbia’s state education agency responsible for overseeing public education policies, programs, and accountability across the city.
  • 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_69a88b074b908190ae983dbca7757d88 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc61c1ef08190911d5f58c2e91189 completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae895f5420819087b403e9772dce9a completed March 9, 2026, 8:48 a.m.
NEDg Description generation batch_69ae8af65eb88190b17d74e7411967cc completed March 9, 2026, 8:55 a.m.
NED2 Entity disambiguation (via description) batch_69ae8ba02cec8190917c0e17d3fedb0e completed March 9, 2026, 8:58 a.m.
Created at: March 4, 2026, 7:49 p.m.