Triple

T3239904
Position Surface form Disambiguated ID Type / Status
Subject Donkey (Shrek) E67941 entity
Predicate child P120 FINISHED
Object Eclair (Dronkey)
Eclair is one of Donkey and Dragon’s hybrid dragon-donkey offspring, known as a dronkey, from the Shrek film series.
E341063 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: Eclair (Dronkey) | Statement: [Donkey (Shrek), child, Eclair (Dronkey)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eclair (Dronkey)
Context triple: [Donkey (Shrek), child, Eclair (Dronkey)]
  • A. The Egg
    The Egg is a modern, student-centered dining and learning facility at the Culinary Institute of America’s Hyde Park campus that showcases culinary education in a real-world restaurant environment.
  • B. The Egg
    The Egg is an iconic, egg-shaped performing arts venue in Albany, New York, known for its distinctive modernist architecture and role as a cultural center.
  • C. Bondoufle
    Bondoufle is a commune in the southern suburbs of Paris, located in the Essonne department in Île-de-France, France.
  • D. Tronchet
    Tronchet is a French surname most notably borne by François Denis Tronchet, an influential 18th–19th century jurist and key figure in drafting the Napoleonic Civil Code.
  • E. Marcel
    Marcel is a masculine given name of French origin, commonly used in various European countries.
  • 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: Eclair (Dronkey)
Triple: [Donkey (Shrek), child, Eclair (Dronkey)]
Generated description
Eclair is one of Donkey and Dragon’s hybrid dragon-donkey offspring, known as a dronkey, from the Shrek film series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Eclair (Dronkey)
Target entity description: Eclair is one of Donkey and Dragon’s hybrid dragon-donkey offspring, known as a dronkey, from the Shrek film series.
  • A. The Egg
    The Egg is an iconic, egg-shaped performing arts venue in Albany, New York, known for its distinctive modernist architecture and role as a cultural center.
  • B. The Egg
    The Egg is a modern, student-centered dining and learning facility at the Culinary Institute of America’s Hyde Park campus that showcases culinary education in a real-world restaurant environment.
  • C. Bondoufle
    Bondoufle is a commune in the southern suburbs of Paris, located in the Essonne department in Île-de-France, France.
  • D. Tronchet
    Tronchet is a French surname most notably borne by François Denis Tronchet, an influential 18th–19th century jurist and key figure in drafting the Napoleonic Civil Code.
  • E. Marcel
    Marcel is a masculine given name of French origin, commonly used in various European countries.
  • 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_69ad858d27348190abb61c280b4c86a9 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaef4c0bc819095e4f84296fe7cb6 completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2774f93448190b8493b457636ae48 completed March 12, 2026, 8:20 a.m.
NEDg Description generation batch_69b2786b7d388190ad0d97bd41a60543 completed March 12, 2026, 8:25 a.m.
NED2 Entity disambiguation (via description) batch_69b27c45f6b08190966fbc3fd28664ec completed March 12, 2026, 8:41 a.m.
Created at: March 8, 2026, 3:08 p.m.