Triple

T476456
Position Surface form Disambiguated ID Type / Status
Subject Harvard Alumni Association E9072 entity
Predicate abbreviation P43 FINISHED
Object HAA
HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
 E59365 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: HAA | Statement: [Harvard Alumni Association, abbreviation, HAA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HAA
Context triple: [Harvard Alumni Association, abbreviation, HAA]
  • A. HAV
    HAV is the IATA airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
  • B. HH
    HH is the vehicle registration code used on license plates for the German city-state of Hamburg.
  • C. harae
    Harae is a central Shinto purification ritual intended to cleanse spiritual impurity and restore harmony between people, nature, and the kami.
  • D. AA
    AA is the two-letter IATA airline designator used to identify American Airlines in flight schedules, tickets, and aviation systems.
  • E. AA
    AA was the common abbreviation for the German Foreign Office (Auswärtiges Amt) during the Nazi era.
  • 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: HAA
Triple: [Harvard Alumni Association, abbreviation, HAA]
Generated description
HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HAA
Target entity description: HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
  • A. HAV
    HAV is the IATA airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
  • B. HH
    HH is the vehicle registration code used on license plates for the German city-state of Hamburg.
  • C. harae
    Harae is a central Shinto purification ritual intended to cleanse spiritual impurity and restore harmony between people, nature, and the kami.
  • D. AA
    AA is the two-letter IATA airline designator used to identify American Airlines in flight schedules, tickets, and aviation systems.
  • E. AA
    AA was the common abbreviation for the German Foreign Office (Auswärtiges Amt) during the Nazi era.
  • 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_69a2e7ff81708190b0507a24a997232c completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f03cc63881908e75b457804cb858 completed Feb. 28, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69a46802cf108190a71d45f1ad3262e2 completed March 1, 2026, 4:23 p.m.
NEDg Description generation batch_69a4686a1c448190943fb889cd26c715 completed March 1, 2026, 4:25 p.m.
NED2 Entity disambiguation (via description) batch_69a468c9f5008190b431bc4bd374ab78 completed March 1, 2026, 4:26 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.