Triple

T14467556
Position Surface form Disambiguated ID Type / Status
Subject Aqua Marcia E358751 entity
Predicate connectedTo P37 FINISHED
Object Aqua Tepula
Aqua Tepula was an ancient Roman aqueduct, one of the earlier systems built to supply fresh water to the city of Rome.
E1101621 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: Aqua Tepula | Statement: [Aqua Marcia, connectedTo, Aqua Tepula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aqua Tepula
Context triple: [Aqua Marcia, connectedTo, Aqua Tepula]
  • A. Aquata
    Aquata is one of King Triton’s mermaid daughters and a princess of Atlantica in Disney’s The Little Mermaid franchise.
  • B. Calliaqua
    Calliaqua is a coastal town in southern Saint Vincent known for its fishing community, marina, and role as a local commercial hub.
  • C. Aur Lagoon
    Aur Lagoon is the central coral-fringed lagoon of Aur Atoll in the Marshall Islands, known for its clear tropical waters and rich marine life.
  • D. Haurietis Aquas
    Haurietis Aquas is a 1956 encyclical of Pope Pius XII that deepens the Catholic Church’s teaching and devotion to the Sacred Heart of Jesus.
  • E. Moon Pool
    The Moon Pool is a notable public square and water-filled basin in the Free City of Braavos in the world of "A Song of Ice and Fire," often associated with commerce, gatherings, and the city's maritime character.
  • 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: Aqua Tepula
Triple: [Aqua Marcia, connectedTo, Aqua Tepula]
Generated description
Aqua Tepula was an ancient Roman aqueduct, one of the earlier systems built to supply fresh water to the city of Rome.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Aqua Tepula
Target entity description: Aqua Tepula was an ancient Roman aqueduct, one of the earlier systems built to supply fresh water to the city of Rome.
  • A. Aquata
    Aquata is one of King Triton’s mermaid daughters and a princess of Atlantica in Disney’s The Little Mermaid franchise.
  • B. Calliaqua
    Calliaqua is a coastal town in southern Saint Vincent known for its fishing community, marina, and role as a local commercial hub.
  • C. Aur Lagoon
    Aur Lagoon is the central coral-fringed lagoon of Aur Atoll in the Marshall Islands, known for its clear tropical waters and rich marine life.
  • D. Haurietis Aquas
    Haurietis Aquas is a 1956 encyclical of Pope Pius XII that deepens the Catholic Church’s teaching and devotion to the Sacred Heart of Jesus.
  • E. Moon Pool
    The Moon Pool is a notable public square and water-filled basin in the Free City of Braavos in the world of "A Song of Ice and Fire," often associated with commerce, gatherings, and the city's maritime character.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91f8613c819080424104c0b7f4c3 completed April 14, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6499c7188190a79411b471cfa7d4 completed May 8, 2026, 4:20 a.m.
NEDg Description generation batch_69fd68a687dc8190bbb1ea24bfdb674b completed May 8, 2026, 4:37 a.m.
NED2 Entity disambiguation (via description) batch_69fd69982e648190b9af4f2895514c3e completed May 8, 2026, 4:42 a.m.
Created at: April 10, 2026, 1:19 a.m.