Triple

T4758753
Position Surface form Disambiguated ID Type / Status
Subject Boedromion E105650 entity
Predicate containsFestival P2955 FINISHED
Object Demetria
Demetria was an ancient Athenian festival held in honor of the goddess Demeter, associated with agriculture and fertility.
 E468441 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: Demetria | Statement: [Boedromion, containsFestival, Demetria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Demetria
Context triple: [Boedromion, containsFestival, Demetria]
  • A. Dameisha
    Dameisha is a popular coastal area in Shenzhen, China, best known for its long sandy beach, seaside resorts, and recreational attractions.
  • B. Drisella
    Drisella is one of Cinderella’s vain and spiteful stepsisters in Disney’s 2015 live-action adaptation of the classic fairy tale.
  • C. Melina
    Melina is a key resistance fighter and love interest in the science fiction film "Total Recall," known for aiding the protagonist in his struggle against a corrupt Martian regime.
  • D. Adrienne
    Adrienne is a feminine given name of French origin, commonly used in English- and French-speaking countries.
  • E. Arletta
    Arletta, better known as Herleva of Falaise, was the mother of William the Conqueror and a notable figure in 11th-century Norman history.
  • 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: Demetria
Triple: [Boedromion, containsFestival, Demetria]
Generated description
Demetria was an ancient Athenian festival held in honor of the goddess Demeter, associated with agriculture and fertility.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Demetria
Target entity description: Demetria was an ancient Athenian festival held in honor of the goddess Demeter, associated with agriculture and fertility.
  • A. Dameisha
    Dameisha is a popular coastal area in Shenzhen, China, best known for its long sandy beach, seaside resorts, and recreational attractions.
  • B. Drisella
    Drisella is one of Cinderella’s vain and spiteful stepsisters in Disney’s 2015 live-action adaptation of the classic fairy tale.
  • C. Melina
    Melina is a key resistance fighter and love interest in the science fiction film "Total Recall," known for aiding the protagonist in his struggle against a corrupt Martian regime.
  • D. Adrienne
    Adrienne is a feminine given name of French origin, commonly used in English- and French-speaking countries.
  • E. Arletta
    Arletta, better known as Herleva of Falaise, was the mother of William the Conqueror and a notable figure in 11th-century Norman history.
  • 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_69bd43f14cac819081c7c69803648211 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd650c11f4819098cd1f490f711dc8 completed March 20, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43b837408190a3de13930e3e5e19 completed March 21, 2026, 7:07 a.m.
NEDg Description generation batch_69be44a60c2c8190b47efae80379b21e completed March 21, 2026, 7:11 a.m.
NED2 Entity disambiguation (via description) batch_69be4530fe5c8190aa976151cdd5bc7a completed March 21, 2026, 7:13 a.m.
Created at: March 20, 2026, 1:20 p.m.