Triple

T9018898
Position Surface form Disambiguated ID Type / Status
Subject Washington Court of Appeals E215662 entity
Predicate citationStyle P4468 FINISHED
Object Wn. App.
Wn. App. is the standard legal citation abbreviation used for published opinions of the Washington Court of Appeals.
 E773259 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: Wn. App. | Statement: [Washington Court of Appeals, citationStyle, Wn. App.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wn. App.
Context triple: [Washington Court of Appeals, citationStyle, Wn. App.]
  • A. WNA
    WNA is the acronym for the World Nuclear Association, an international organization that promotes the peaceful use and development of nuclear power worldwide.
  • B. WNL
    WNL is the National Rail station code for Whinhill railway station in Inverclyde, Scotland.
  • C. WICA
    WICA is the ICAO airport code assigned to Kertajati International Airport in West Java, Indonesia.
  • D. W.D. N.C.
    W.D. N.C. is the standard legal abbreviation for the United States District Court for the Western District of North Carolina, a federal trial court within the Fourth Circuit.
  • E. Court of Appeals of Virginia
    The Court of Appeals of Virginia is an intermediate appellate court that reviews decisions from Virginia’s trial courts and certain state agencies before possible review by the Supreme Court of Virginia.
  • 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: Wn. App.
Triple: [Washington Court of Appeals, citationStyle, Wn. App.]
Generated description
Wn. App. is the standard legal citation abbreviation used for published opinions of the Washington Court of Appeals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wn. App.
Target entity description: Wn. App. is the standard legal citation abbreviation used for published opinions of the Washington Court of Appeals.
  • A. WNA
    WNA is the acronym for the World Nuclear Association, an international organization that promotes the peaceful use and development of nuclear power worldwide.
  • B. WNL
    WNL is the National Rail station code for Whinhill railway station in Inverclyde, Scotland.
  • C. WICA
    WICA is the ICAO airport code assigned to Kertajati International Airport in West Java, Indonesia.
  • D. W.D. N.C.
    W.D. N.C. is the standard legal abbreviation for the United States District Court for the Western District of North Carolina, a federal trial court within the Fourth Circuit.
  • E. Court of Appeals of Virginia
    The Court of Appeals of Virginia is an intermediate appellate court that reviews decisions from Virginia’s trial courts and certain state agencies before possible review by the Supreme Court of Virginia.
  • 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_69ca83a38aa88190bf1bb80c4548b5e2 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6a4085848190a6aa440e6307e93d completed April 1, 2026, 12:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbaf7be081908738ef9a9a17a77b completed April 3, 2026, 3:24 p.m.
NEDg Description generation batch_69cfdd06e9cc8190a1df43556d91779d completed April 3, 2026, 3:30 p.m.
NED2 Entity disambiguation (via description) batch_69cfdda4bf048190bc054fe9b1dcc98d completed April 3, 2026, 3:32 p.m.
Created at: March 30, 2026, 7:07 p.m.