Triple

T16993300
Position Surface form Disambiguated ID Type / Status
Subject Pon de Replay E412246 entity
Predicate writer P1360 FINISHED
Object Alisha Brooks
Alisha Brooks is a songwriter best known for co-writing Rihanna’s breakout hit single "Pon de Replay."
E1244025 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: Alisha Brooks | Statement: [Pon de Replay, writer, Alisha Brooks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alisha Brooks
Context triple: [Pon de Replay, writer, Alisha Brooks]
  • A. Alisha Daniels
    Alisha Daniels is a central character in the British TV series "Misfits," known for her initially problematic power related to sexual arousal and her complex personal growth throughout the show.
  • B. Aleisha Allen
    Aleisha Allen is an American actress best known for her childhood roles in films such as "Are We There Yet?" and "School of Rock."
  • C. Alisha Bailey
    Alisha Bailey is an actress known for her role in the action film "Backdraft 2."
  • D. Alisha Newton
    Alisha Newton is a Canadian actress best known for playing Georgie Fleming Morris on the long-running family drama series "Heartland."
  • E. Kendra Foster
    Kendra Foster is an American singer-songwriter and Grammy-winning collaborator best known for her work with D'Angelo and Parliament-Funkadelic.
  • 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: Alisha Brooks
Triple: [Pon de Replay, writer, Alisha Brooks]
Generated description
Alisha Brooks is a songwriter best known for co-writing Rihanna’s breakout hit single "Pon de Replay."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alisha Brooks
Target entity description: Alisha Brooks is a songwriter best known for co-writing Rihanna’s breakout hit single "Pon de Replay."
  • A. Alisha Daniels
    Alisha Daniels is a central character in the British TV series "Misfits," known for her initially problematic power related to sexual arousal and her complex personal growth throughout the show.
  • B. Aleisha Allen
    Aleisha Allen is an American actress best known for her childhood roles in films such as "Are We There Yet?" and "School of Rock."
  • C. Alisha Bailey
    Alisha Bailey is an actress known for her role in the action film "Backdraft 2."
  • D. Alisha Newton
    Alisha Newton is a Canadian actress best known for playing Georgie Fleming Morris on the long-running family drama series "Heartland."
  • E. Kendra Foster
    Kendra Foster is an American singer-songwriter and Grammy-winning collaborator best known for her work with D'Angelo and Parliament-Funkadelic.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d28535788190bdfcb6201a9024b5 completed April 18, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc16fbdc819095411a056b9942c3 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a00dc96a9588190b020fd7fd1deee2b completed May 10, 2026, 7:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0114e04e00819093805024f8417fad completed May 10, 2026, 11:29 p.m.
Created at: April 10, 2026, 5:32 a.m.