Triple

T12653797
Position Surface form Disambiguated ID Type / Status
Subject Loma E302229 entity
Predicate ISO639-3Code P208 FINISHED
Object lom
lom is the ISO 639-3 language code for the Loma language spoken primarily in Liberia and neighboring West African regions.
 E996628 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: lom | Statement: [Loma, ISO639-3Code, lom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: lom
Context triple: [Loma, ISO639-3Code, lom]
  • A. Lom
    Lom is a mountainous municipality in Innlandet county, Norway, known for its historic stave church and as a gateway to the Jotunheimen National Park.
  • B. LOM
    LOM is the official abbreviation for the Legion of Merit, a prestigious United States military decoration awarded for exceptionally meritorious conduct in the performance of outstanding services and achievements.
  • C. LÖ
    LÖ is the vehicle registration code for the district of Lörrach in the German state of Baden-Württemberg.
  • D. LMO
    LMO is the IATA airport code for RAF Lossiemouth, a Royal Air Force station and military airfield in Moray, Scotland.
  • E. Lo
    Lo is a short form of the Dutch given name Lodewijk, commonly used as an informal or affectionate nickname.
  • 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: lom
Triple: [Loma, ISO639-3Code, lom]
Generated description
lom is the ISO 639-3 language code for the Loma language spoken primarily in Liberia and neighboring West African regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: lom
Target entity description: lom is the ISO 639-3 language code for the Loma language spoken primarily in Liberia and neighboring West African regions.
  • A. Lom
    Lom is a mountainous municipality in Innlandet county, Norway, known for its historic stave church and as a gateway to the Jotunheimen National Park.
  • B. LOM
    LOM is the official abbreviation for the Legion of Merit, a prestigious United States military decoration awarded for exceptionally meritorious conduct in the performance of outstanding services and achievements.
  • C. LÖ
    LÖ is the vehicle registration code for the district of Lörrach in the German state of Baden-Württemberg.
  • D. LMO
    LMO is the IATA airport code for RAF Lossiemouth, a Royal Air Force station and military airfield in Moray, Scotland.
  • E. Lo
    Lo is a short form of the Dutch given name Lodewijk, commonly used as an informal or affectionate nickname.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96160730c81909e1aa3efb51bf159 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6688104d48190939933b93b7e60cc completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f66c572f848190a8cad6311d3315a3 completed May 2, 2026, 9:27 p.m.
NED2 Entity disambiguation (via description) batch_69f66cef79148190a052fb9ade3b0d27 completed May 2, 2026, 9:30 p.m.
Created at: April 9, 2026, 5:18 p.m.