Triple

T5082273
Position Surface form Disambiguated ID Type / Status
Subject Macy’s Thanksgiving Day Parade E114543 entity
Predicate typicalInPersonAttendance P57039 FINISHED
Object hundreds of thousands of spectators LITERAL FINISHED

How this triple was built (2 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: hundreds of thousands of spectators | Statement: [Macy’s Thanksgiving Day Parade, typicalInPersonAttendance, hundreds of thousands of spectators]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalInPersonAttendance
Context triple: [Macy’s Thanksgiving Day Parade, typicalInPersonAttendance, hundreds of thousands of spectators]
  • A. attendanceInfluence
    Indicates how one entity’s presence or participation affects the attendance level or likelihood of attendance of another entity or group.
  • B. attendance
    Indicates the relationship between an event and the people who are present at or participate in that event.
  • C. attendancePromotion
    Indicates a relationship where one entity promotes, encourages, or incentivizes attendance at an event, activity, or location for another entity.
  • D. attendanceAnnounced
    Indicates that an official statement has been made about whether and/or how many people will attend an event.
  • E. averageAttendanceCategory chosen
    Indicates the attendance range or classification into which an entity’s typical or mean attendance level falls.
  • F. None of above.

Provenance (3 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_69bd443dbf908190a9401e9c2dc7bd7d completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd74fb3df4819082bd8ae64e207ceb completed March 20, 2026, 4:25 p.m.
PD Predicate disambiguation batch_69bd7159adc881909effd4382c395c66 completed March 20, 2026, 4:10 p.m.
Created at: March 20, 2026, 1:39 p.m.