Triple

T3846395
Position Surface form Disambiguated ID Type / Status
Subject Cerveteri E93579 entity
Predicate historicalName P65 FINISHED
Object Agylla
Agylla is the ancient Etruscan city later known as Cerveteri, a major center of Etruscan civilization in central Italy.
 E394012 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: Agylla | Statement: [Cerveteri, historicalName, Agylla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Agylla
Context triple: [Cerveteri, historicalName, Agylla]
  • A. Roxeth
    Roxeth is a residential district in the London Borough of Harrow, northwest London, known for its suburban character and proximity to Harrow-on-the-Hill.
  • B. Carneia
    Carneia was an important ancient Spartan and Dorian festival in honor of Apollo, marked by rituals, music, and athletic contests that reflected both military and agricultural aspects of the community.
  • C. Valla
    Valla is an Italian surname most famously associated with Renaissance humanist and philologist Lorenzo Valla.
  • D. Lothagam
    Lothagam is an archaeological and geological site in northern Kenya known for its ancient human burials and prominent rock formations along the western shore of Lake Turkana.
  • E. Ascra
    Ascra was an ancient village in Boeotia, Greece, best known as the hometown of the poet Hesiod.
  • 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: Agylla
Triple: [Cerveteri, historicalName, Agylla]
Generated description
Agylla is the ancient Etruscan city later known as Cerveteri, a major center of Etruscan civilization in central Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Agylla
Target entity description: Agylla is the ancient Etruscan city later known as Cerveteri, a major center of Etruscan civilization in central Italy.
  • A. Roxeth
    Roxeth is a residential district in the London Borough of Harrow, northwest London, known for its suburban character and proximity to Harrow-on-the-Hill.
  • B. Carneia
    Carneia was an important ancient Spartan and Dorian festival in honor of Apollo, marked by rituals, music, and athletic contests that reflected both military and agricultural aspects of the community.
  • C. Valla
    Valla is an Italian surname most famously associated with Renaissance humanist and philologist Lorenzo Valla.
  • D. Lothagam
    Lothagam is an archaeological and geological site in northern Kenya known for its ancient human burials and prominent rock formations along the western shore of Lake Turkana.
  • E. Ascra
    Ascra was an ancient village in Boeotia, Greece, best known as the hometown of the poet Hesiod.
  • 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_69aed96ce578819084ab16e3439976c9 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeebb77a488190be7fc2a1211f1f2d completed March 9, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b50414acdc81909bf0b62afa3fe536 completed March 14, 2026, 6:45 a.m.
NEDg Description generation batch_69b50585106c8190aaa1c47b397543ea completed March 14, 2026, 6:51 a.m.
NED2 Entity disambiguation (via description) batch_69b50707d6a4819097f2bca0ebe663b1 completed March 14, 2026, 6:58 a.m.
Created at: March 9, 2026, 3:18 p.m.