Triple

T14825423
Position Surface form Disambiguated ID Type / Status
Subject Welsh Office E348557 entity
Predicate hasAbbreviation P43 FINISHED
Object WO
WO is the abbreviation for the Welsh Office, a former UK government department responsible for Welsh affairs.
 E1122682 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: WO | Statement: [Welsh Office, hasAbbreviation, WO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WO
Context triple: [Welsh Office, hasAbbreviation, WO]
  • A. OW
    OW is the official vehicle registration code used on license plates for the Swiss canton of Obwalden.
  • B. W
    The W is a local New York City Subway service that runs on the BMT Broadway Line in Manhattan and Queens, typically operating on weekdays.
  • C. W
    W is one of the iconic white capital letters that make up the famous Hollywood Sign overlooking Los Angeles.
  • D. WE
    WE is Arcade Fire’s 2022 studio album, a concept-driven indie rock record exploring themes of isolation, connection, and the modern human condition.
  • E. WR
    WR is the abbreviation for the German Council of Science and Humanities, a key advisory body that counsels the German federal and state governments on science, research, and higher education policy.
  • 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: WO
Triple: [Welsh Office, hasAbbreviation, WO]
Generated description
WO is the abbreviation for the Welsh Office, a former UK government department responsible for Welsh affairs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WO
Target entity description: WO is the abbreviation for the Welsh Office, a former UK government department responsible for Welsh affairs.
  • A. OW
    OW is the official vehicle registration code used on license plates for the Swiss canton of Obwalden.
  • B. W
    W is one of the iconic white capital letters that make up the famous Hollywood Sign overlooking Los Angeles.
  • C. W
    The W is a local New York City Subway service that runs on the BMT Broadway Line in Manhattan and Queens, typically operating on weekdays.
  • D. WE
    WE is Arcade Fire’s 2022 studio album, a concept-driven indie rock record exploring themes of isolation, connection, and the modern human condition.
  • E. WR
    WR is the abbreviation for the German Council of Science and Humanities, a key advisory body that counsels the German federal and state governments on science, research, and higher education policy.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded0713700819097bbb0352650984b completed April 14, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389f48cc819089d860f0208dd465 completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe3a2167348190bb428c7f23ec9748 completed May 8, 2026, 7:31 p.m.
NED2 Entity disambiguation (via description) batch_69fe3aee9d248190b202c7252f290f38 completed May 8, 2026, 7:35 p.m.
Created at: April 10, 2026, 1:51 a.m.