Triple

T22191434
Position Surface form Disambiguated ID Type / Status
Subject Interest on Lawyers’ Trust Accounts program E548434 entity
Predicate hasAcronym P43 FINISHED
Object IOLTA
IOLTA is a program that collects interest earned on lawyers’ pooled client trust accounts to fund legal aid and other public interest legal services.
E1524718 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: IOLTA | Statement: [Interest on Lawyers’ Trust Accounts program, hasAcronym, IOLTA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IOLTA
Context triple: [Interest on Lawyers’ Trust Accounts program, hasAcronym, IOLTA]
  • A. LITA
    LITA is the radio callsign assigned to the Norwegian royal yacht Norge.
  • B. LGC
    LGC is the three-letter IATA airport code for LaGrange–Callaway Airport in LaGrange, Georgia, United States.
  • C. OIA
    OIA is a common acronym for an Office of International Affairs, typically a governmental or institutional body that manages international relations, partnerships, and global programs.
  • D. HOLAC
    HOLAC is the acronym commonly used for the House of Lords Appointments Commission, the independent body that recommends individuals for appointment to the UK House of Lords.
  • E. HLLB
    HLLB is the ICAO airport code for Benina International Airport, the main airport serving Benghazi in eastern Libya.
  • 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: IOLTA
Triple: [Interest on Lawyers’ Trust Accounts program, hasAcronym, IOLTA]
Generated description
IOLTA is a program that collects interest earned on lawyers’ pooled client trust accounts to fund legal aid and other public interest legal services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: IOLTA
Target entity description: IOLTA is a program that collects interest earned on lawyers’ pooled client trust accounts to fund legal aid and other public interest legal services.
  • A. LITA
    LITA is the radio callsign assigned to the Norwegian royal yacht Norge.
  • B. LGC
    LGC is the three-letter IATA airport code for LaGrange–Callaway Airport in LaGrange, Georgia, United States.
  • C. OIA
    OIA is a common acronym for an Office of International Affairs, typically a governmental or institutional body that manages international relations, partnerships, and global programs.
  • D. HOLAC
    HOLAC is the acronym commonly used for the House of Lords Appointments Commission, the independent body that recommends individuals for appointment to the UK House of Lords.
  • E. HLLB
    HLLB is the ICAO airport code for Benina International Airport, the main airport serving Benghazi in eastern Libya.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12ae3e8148190a23decd2dfe24e28 completed April 28, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0aa60c29608190afef2bcae36e4c12 completed May 18, 2026, 5:39 a.m.
NEDg Description generation batch_6a0aa73b63008190955cdfc17063c405 completed May 18, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_6a0aa7ab0d108190a907cba7075bddd8 completed May 18, 2026, 5:46 a.m.
Created at: April 16, 2026, 8:35 p.m.