Triple

T5780666
Position Surface form Disambiguated ID Type / Status
Subject Ras Baraka E127546 entity
Predicate twitterHandle P2866 FINISHED
Object @rasjbaraka
@rasjbaraka is the Twitter handle of Ras Baraka, the mayor of Newark, New Jersey and a prominent educator, activist, and political leader.
 E545262 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: @rasjbaraka | Statement: [Ras Baraka, twitterHandle, @rasjbaraka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: @rasjbaraka
Context triple: [Ras Baraka, twitterHandle, @rasjbaraka]
  • A. RAJ
    RAJ is the IATA airport code for Rajkot Airport, which serves the city of Rajkot in the Indian state of Gujarat.
  • B. RAS
    RAS is the commonly used abbreviation for the Royal Astronomical Society, a leading learned society dedicated to the advancement of astronomy and geophysics.
  • C. JRB
    JRB is the IATA airport code for the Wall Street Heliport serving lower Manhattan in New York City.
  • D. RJAH
    RJAH is the ICAO airport code for Hyakuri Air Base, a Japanese military airfield in Ibaraki Prefecture.
  • E. RJ
    RJ is the two-letter IATA airline designator assigned to Royal Jordanian, the flag carrier airline of Jordan.
  • 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: @rasjbaraka
Triple: [Ras Baraka, twitterHandle, @rasjbaraka]
Generated description
@rasjbaraka is the Twitter handle of Ras Baraka, the mayor of Newark, New Jersey and a prominent educator, activist, and political leader.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: @rasjbaraka
Target entity description: @rasjbaraka is the Twitter handle of Ras Baraka, the mayor of Newark, New Jersey and a prominent educator, activist, and political leader.
  • A. RAJ
    RAJ is the IATA airport code for Rajkot Airport, which serves the city of Rajkot in the Indian state of Gujarat.
  • B. RAS
    RAS is the commonly used abbreviation for the Royal Astronomical Society, a leading learned society dedicated to the advancement of astronomy and geophysics.
  • C. JRB
    JRB is the IATA airport code for the Wall Street Heliport serving lower Manhattan in New York City.
  • D. RJAH
    RJAH is the ICAO airport code for Hyakuri Air Base, a Japanese military airfield in Ibaraki Prefecture.
  • E. RJ
    RJ is the two-letter IATA airline designator assigned to Royal Jordanian, the flag carrier airline of Jordan.
  • 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_69c008361fa88190aefa4dc41b051e7f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c029e3f88c8190975921ff2912e543 completed March 22, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e7773888190bd8c3e1d7df62f5c completed March 22, 2026, 11:42 p.m.
NEDg Description generation batch_69c086cd0904819089dbacd6c948abec completed March 23, 2026, 12:18 a.m.
NED2 Entity disambiguation (via description) batch_69c0873661788190847751ba82975e82 completed March 23, 2026, 12:20 a.m.
Created at: March 22, 2026, 3:50 p.m.