Triple

T1249869
Position Surface form Disambiguated ID Type / Status
Subject Pyrgi Tablets E26849 entity
Predicate associatedDeity P1481 FINISHED
Object Uni
Uni is an Etruscan goddess, broadly equivalent to the Roman Juno and Greek Hera, associated with marriage, fertility, and protection of the state.
 E143944 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: Uni | Statement: [Pyrgi Tablets, associatedDeity, Uni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Uni
Context triple: [Pyrgi Tablets, associatedDeity, Uni]
  • A. SU
    SU is the IATA airline designator for Aeroflot, Russia’s flag carrier and largest airline.
  • B. SU
    SU was the two-letter country code used to represent the former Soviet Union in various international standards and systems.
  • C. UA
    UA is a major public research university located in Tucson, Arizona, known for its strong programs in astronomy, space sciences, and environmental studies.
  • D. UA
    UA is the two-letter IATA airline designator used worldwide to identify United Airlines on tickets, schedules, and flight information.
  • E. UA
    UA is the two-letter ISO 3166-1 alpha-2 country code assigned to Ukraine for international standardization and identification purposes.
  • 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: Uni
Triple: [Pyrgi Tablets, associatedDeity, Uni]
Generated description
Uni is an Etruscan goddess, broadly equivalent to the Roman Juno and Greek Hera, associated with marriage, fertility, and protection of the state.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Uni
Target entity description: Uni is an Etruscan goddess, broadly equivalent to the Roman Juno and Greek Hera, associated with marriage, fertility, and protection of the state.
  • A. SU
    SU was the two-letter country code used to represent the former Soviet Union in various international standards and systems.
  • B. SU
    SU is the IATA airline designator for Aeroflot, Russia’s flag carrier and largest airline.
  • C. UA
    UA is the two-letter IATA airline designator used worldwide to identify United Airlines on tickets, schedules, and flight information.
  • D. UA
    UA is a major public research university located in Tucson, Arizona, known for its strong programs in astronomy, space sciences, and environmental studies.
  • E. UA
    UA is the two-letter ISO 3166-1 alpha-2 country code assigned to Ukraine for international standardization and identification purposes.
  • 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_69a49487a9c48190ba9b05348fd1b53f completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4bf83b32c81908648e5748b897247 completed March 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac93c66bf881908f4b63548341178e completed March 7, 2026, 9:08 p.m.
NEDg Description generation batch_69ac943de3f0819085dff5ef12f01766 completed March 7, 2026, 9:10 p.m.
NED2 Entity disambiguation (via description) batch_69ac95c05ab081909db602d7bea73bf4 completed March 7, 2026, 9:16 p.m.
Created at: March 1, 2026, 7:47 p.m.