Triple

T2831706
Position Surface form Disambiguated ID Type / Status
Subject Rambo III E62251 entity
Predicate starring P1507 FINISHED
Object Marc de Jonge
Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
E302334 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: Marc de Jonge | Statement: [Rambo III, starring, Marc de Jonge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc de Jonge
Context triple: [Rambo III, starring, Marc de Jonge]
  • A. Adrian Sweere
    Adrian Sweere was an early 20th-century Jesuit priest and educator who played a key role in establishing what would become Seattle University.
  • B. Bete Denagel
    Bete Denagel is one of the rock-hewn monolithic churches in the historic Ethiopian town of Lalibela, renowned for its medieval Christian architecture and religious significance.
  • C. Christian Huitema
    Christian Huitema is a French computer scientist and Internet pioneer known for his influential work on networking protocols and IPv6 transition technologies.
  • D. Tim Kruithoff
    Tim Kruithoff is a German local politician who serves as the mayor of the city of Emden in Lower Saxony.
  • E. Jan-Christian Dreesen
    Jan-Christian Dreesen is a German football executive best known for serving as the chief executive officer of FC Bayern Munich.
  • 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: Marc de Jonge
Triple: [Rambo III, starring, Marc de Jonge]
Generated description
Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marc de Jonge
Target entity description: Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
  • A. Adrian Sweere
    Adrian Sweere was an early 20th-century Jesuit priest and educator who played a key role in establishing what would become Seattle University.
  • B. Bete Denagel
    Bete Denagel is one of the rock-hewn monolithic churches in the historic Ethiopian town of Lalibela, renowned for its medieval Christian architecture and religious significance.
  • C. Christian Huitema
    Christian Huitema is a French computer scientist and Internet pioneer known for his influential work on networking protocols and IPv6 transition technologies.
  • D. Tim Kruithoff
    Tim Kruithoff is a German local politician who serves as the mayor of the city of Emden in Lower Saxony.
  • E. Jan-Christian Dreesen
    Jan-Christian Dreesen is a German football executive best known for serving as the chief executive officer of FC Bayern Munich.
  • 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_69ab4c3c39188190955b9c49d98463d8 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdebe95188190bf65fb4cd88e2ec5 completed March 7, 2026, 8:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69afceb771d48190a1467a6e58f756ad completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afd21bf66481909d0416cf591fc2cf completed March 10, 2026, 8:11 a.m.
NED2 Entity disambiguation (via description) batch_69afd28839a881909c758e2ea202242a completed March 10, 2026, 8:12 a.m.
Created at: March 6, 2026, 10:01 p.m.