Triple

T4263290
Position Surface form Disambiguated ID Type / Status
Subject Marty Panzer E96154 entity
Predicate wroteLyricsForSong P1360 FINISHED
Object “Sandra”
“Sandra” is a song with lyrics by American songwriter Marty Panzer, known for his emotive and narrative-driven pop compositions.
 E425895 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: “Sandra” | Statement: [Marty Panzer, wroteLyricsForSong, “Sandra”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: “Sandra”
Context triple: [Marty Panzer, wroteLyricsForSong, “Sandra”]
  • A. Sandra
    Sandra is the given name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
  • B. Sandi
    Sandi is a given name, typically a variant of Sandy, used for both males and females.
  • C. Sondra
    Sondra is a feminine given name, often considered a variant of Sandra or Alexandra.
  • D. Sarah Sands
    Sarah Sands is a British journalist and editor best known for her leadership roles at major UK publications, including serving as editor of the London Evening Standard and later as editor of BBC Radio 4’s Today programme.
  • E. Sandy Vee
    Sandy Vee is a French record producer and songwriter known for crafting international pop and dance hits for artists such as Rihanna.
  • 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: “Sandra”
Triple: [Marty Panzer, wroteLyricsForSong, “Sandra”]
Generated description
“Sandra” is a song with lyrics by American songwriter Marty Panzer, known for his emotive and narrative-driven pop compositions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: “Sandra”
Target entity description: “Sandra” is a song with lyrics by American songwriter Marty Panzer, known for his emotive and narrative-driven pop compositions.
  • A. Sandra
    Sandra is the given name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
  • B. Sandi
    Sandi is a given name, typically a variant of Sandy, used for both males and females.
  • C. Sondra
    Sondra is a feminine given name, often considered a variant of Sandra or Alexandra.
  • D. Sarah Sands
    Sarah Sands is a British journalist and editor best known for her leadership roles at major UK publications, including serving as editor of the London Evening Standard and later as editor of BBC Radio 4’s Today programme.
  • E. Sandy Vee
    Sandy Vee is a French record producer and songwriter known for crafting international pop and dance hits for artists such as Rihanna.
  • 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_69b3454095ac81909c2494f7ff294af1 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34fc821ec8190a7204aaf89d24a6b completed March 12, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b78ffbf881909d59faae665abd36 completed March 14, 2026, 7:31 p.m.
NEDg Description generation batch_69b5b89fe2b08190960a3deaceb75c85 completed March 14, 2026, 7:36 p.m.
NED2 Entity disambiguation (via description) batch_69b5b8ddaa9c8190bc7dc46593cbb8cd completed March 14, 2026, 7:37 p.m.
Created at: March 12, 2026, 11:06 p.m.