Triple

T16065554
Position Surface form Disambiguated ID Type / Status
Subject Juno Temple E389721 entity
Predicate actedIn P1668 FINISHED
Object Dirty Girl
Dirty Girl is a 2010 coming-of-age comedy film about a rebellious Oklahoma teen who embarks on a road trip to find her father, starring Juno Temple in the lead role.
E1193555 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: Dirty Girl | Statement: [Juno Temple, actedIn, Dirty Girl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dirty Girl
Context triple: [Juno Temple, actedIn, Dirty Girl]
  • A. Damn Girl
    "Damn Girl" is a funk-influenced dance track by Justin Timberlake featuring will.i.am from his 2006 album FutureSex/LoveSounds.
  • B. Bad Girl
    "Bad Girl" is a high-energy R&B/pop single by Danity Kane known for its club-ready production and confident, empowering lyrics.
  • C. Bad Girl
    "Bad Girl" is a track from the album "Erotica," known for its provocative themes and sensual style.
  • D. Dream Girl
    Dream Girl is a popular Indian romantic comedy film produced by Ekta Kapoor, known for its quirky premise and humorous take on love and identity.
  • E. Dream Girl
    "Dream Girl" is a song from the album "Chocolate Factory," likely characterized by romantic themes and smooth, R&B-influenced production.
  • 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: Dirty Girl
Triple: [Juno Temple, actedIn, Dirty Girl]
Generated description
Dirty Girl is a 2010 coming-of-age comedy film about a rebellious Oklahoma teen who embarks on a road trip to find her father, starring Juno Temple in the lead role.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dirty Girl
Target entity description: Dirty Girl is a 2010 coming-of-age comedy film about a rebellious Oklahoma teen who embarks on a road trip to find her father, starring Juno Temple in the lead role.
  • A. Damn Girl
    "Damn Girl" is a funk-influenced dance track by Justin Timberlake featuring will.i.am from his 2006 album FutureSex/LoveSounds.
  • B. Bad Girl
    "Bad Girl" is a high-energy R&B/pop single by Danity Kane known for its club-ready production and confident, empowering lyrics.
  • C. Bad Girl
    "Bad Girl" is a track from the album "Erotica," known for its provocative themes and sensual style.
  • D. Dream Girl
    Dream Girl is a popular Indian romantic comedy film produced by Ekta Kapoor, known for its quirky premise and humorous take on love and identity.
  • E. Dream Girl
    "Dream Girl" is a song from the album "Chocolate Factory," likely characterized by romantic themes and smooth, R&B-influenced production.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837bec688190a77ad347600b6bdc completed April 17, 2026, 12:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe47ef6648190bf1fe216e78ef660 completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe5a4edfc8190831ddf8a4601764e completed May 10, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69ffe687c204819092a4a8de0b9d624d completed May 10, 2026, 1:59 a.m.
Created at: April 10, 2026, 4:57 a.m.