Triple

T5692987
Position Surface form Disambiguated ID Type / Status
Subject Forgetting Sarah Marshall E125469 entity
Predicate mainCharacter P1183 FINISHED
Object Rachel Jansen
Rachel Jansen is a kind-hearted hotel receptionist in Hawaii who becomes the new love interest of the heartbroken protagonist in the romantic comedy film "Forgetting Sarah Marshall."
E557677 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: Rachel Jansen | Statement: [Forgetting Sarah Marshall, mainCharacter, Rachel Jansen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rachel Jansen
Context triple: [Forgetting Sarah Marshall, mainCharacter, Rachel Jansen]
  • A. Rachel Schpitendavel
    Rachel Schpitendavel is a fictional character from the 1968 burlesque-themed comedy film "The Night They Raided Minsky's."
  • B. Virginia Jansen
    Virginia Jansen is known as the spouse of American choral and orchestral conductor Robert Shaw.
  • C. Tessa Berens
    Tessa Berens is a fictional character from the work titled "The Silence."
  • D. Emily de Jongh-Elhage
    Emily de Jongh-Elhage is a Curaçaoan politician who served as the final head of government of the Netherlands Antilles before its dissolution in 2010.
  • E. Sarah Junner
    Sarah Junner was the mother of British archaeologist, soldier, and writer T. E. Lawrence, better known as "Lawrence of Arabia."
  • 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: Rachel Jansen
Triple: [Forgetting Sarah Marshall, mainCharacter, Rachel Jansen]
Generated description
Rachel Jansen is a kind-hearted hotel receptionist in Hawaii who becomes the new love interest of the heartbroken protagonist in the romantic comedy film "Forgetting Sarah Marshall."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rachel Jansen
Target entity description: Rachel Jansen is a kind-hearted hotel receptionist in Hawaii who becomes the new love interest of the heartbroken protagonist in the romantic comedy film "Forgetting Sarah Marshall."
  • A. Rachel Schpitendavel
    Rachel Schpitendavel is a fictional character from the 1968 burlesque-themed comedy film "The Night They Raided Minsky's."
  • B. Virginia Jansen
    Virginia Jansen is known as the spouse of American choral and orchestral conductor Robert Shaw.
  • C. Tessa Berens
    Tessa Berens is a fictional character from the work titled "The Silence."
  • D. Emily de Jongh-Elhage
    Emily de Jongh-Elhage is a Curaçaoan politician who served as the final head of government of the Netherlands Antilles before its dissolution in 2010.
  • E. Sarah Junner
    Sarah Junner was the mother of British archaeologist, soldier, and writer T. E. Lawrence, better known as "Lawrence of Arabia."
  • 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_69c0082bb19c8190823a4facd3cba79b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023e678c48190824d35d276985311 completed March 22, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e32cce548190898c735f8c494415 completed March 23, 2026, 6:52 a.m.
NEDg Description generation batch_69c0e66e96c481909133503f553d4bc4 completed March 23, 2026, 7:06 a.m.
NED2 Entity disambiguation (via description) batch_69c0e6c3ec548190814b44fe953ab25e completed March 23, 2026, 7:07 a.m.
Created at: March 22, 2026, 3:44 p.m.