Triple

T19001380
Position Surface form Disambiguated ID Type / Status
Subject Grease (1993 London production) E464960 entity
Predicate featuresCharacter P626 FINISHED
Object Jan
Jan is one of the Pink Ladies, a bubbly and food-loving high school girl in the musical Grease.
E1353423 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: Jan | Statement: [Grease (1993 London production), featuresCharacter, Jan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan
Context triple: [Grease (1993 London production), featuresCharacter, Jan]
  • A. Jan
    Jan is the Dutch given name of Jan Peter Balkenende, the former Prime Minister of the Netherlands.
  • B. Jan
    Jan is an alternative romanization of the name Zhan, used to represent the same underlying name in different transliteration systems.
  • C. Jan
    Jan is one of the central comic characters in Alan Ayckbourn’s stage play "Bedroom Farce," involved in the interwoven marital mishaps that drive the farcical plot.
  • D. Jan
    Jan is a common Dutch given name, often used as a masculine form of "John" and borne by many notable figures in the Netherlands and other Dutch-speaking regions.
  • E. Jan
    Jan is a common Czech given name, equivalent to "John" in English.
  • 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: Jan
Triple: [Grease (1993 London production), featuresCharacter, Jan]
Generated description
Jan is one of the Pink Ladies, a bubbly and food-loving high school girl in the musical Grease.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jan
Target entity description: Jan is one of the Pink Ladies, a bubbly and food-loving high school girl in the musical Grease.
  • A. Jan
    Jan is a fictional character appearing in the Traveling Wilburys’ song “Tweeter and the Monkey Man,” which tells a noir-style crime story.
  • B. Jan
    Jan is the stage name and nickname of Jan Berry, best known as half of the 1960s American rock and roll duo Jan and Dean.
  • C. Jan
    Jan is a feminine given name used in various cultures, often as a form of Johanna or Jane.
  • D. Jan
    Jan is a fictional young soldier and one of the core members of DC Comics' World War II-era kid commando team, the Boy Commandos.
  • E. Jan
    Jan is the main character of the work "The Misunderstanding," around whom the story’s central conflicts and themes revolve.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6863cf4819096e471d19f9a714c completed April 20, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05b45b9ca0819090a85f5708e9c632 completed May 14, 2026, 11:39 a.m.
NEDg Description generation batch_6a05b68205948190a6846e2cd8ba66ae completed May 14, 2026, 11:48 a.m.
NED2 Entity disambiguation (via description) batch_6a05b73aa91c8190abe816e72d2f56f7 completed May 14, 2026, 11:51 a.m.
Created at: April 10, 2026, 12:01 p.m.