Triple

T9339016
Position Surface form Disambiguated ID Type / Status
Subject Desiderius E224717 entity
Predicate spouse P13 FINISHED
Object Ansa
Ansa was a Lombard queen consort of the 8th century, known as the wife of King Desiderius and a significant political and religious patron in the Lombard kingdom.
E792486 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: Ansa | Statement: [Desiderius, spouse, Ansa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ansa
Context triple: [Desiderius, spouse, Ansa]
  • A. Meduza
    Meduza is an Italian electronic music production trio best known for their chart-topping house tracks like "Piece of Your Heart" and "Lose Control."
  • B. Al-Sharq al-Awsat
    Al-Sharq al-Awsat is a prominent London-based pan-Arab daily newspaper known for its wide circulation and influence across the Arab world.
  • C. Warta
    Warta is a major river in western-central Poland that flows through several important cities before joining the Oder River.
  • D. Reut
    Reut is a small municipality in Bavaria, Germany, located near the town of Simbach am Inn close to the Austrian border.
  • E. Al-Ahram newspaper
    Al-Ahram newspaper is one of Egypt’s oldest and most influential daily newspapers, widely regarded as a leading voice in the Arab media landscape.
  • 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: Ansa
Triple: [Desiderius, spouse, Ansa]
Generated description
Ansa was a Lombard queen consort of the 8th century, known as the wife of King Desiderius and a significant political and religious patron in the Lombard kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ansa
Target entity description: Ansa was a Lombard queen consort of the 8th century, known as the wife of King Desiderius and a significant political and religious patron in the Lombard kingdom.
  • A. Meduza
    Meduza is an Italian electronic music production trio best known for their chart-topping house tracks like "Piece of Your Heart" and "Lose Control."
  • B. Al-Sharq al-Awsat
    Al-Sharq al-Awsat is a prominent London-based pan-Arab daily newspaper known for its wide circulation and influence across the Arab world.
  • C. Warta
    Warta is a major river in western-central Poland that flows through several important cities before joining the Oder River.
  • D. Reut
    Reut is a small municipality in Bavaria, Germany, located near the town of Simbach am Inn close to the Austrian border.
  • E. Al-Ahram newspaper
    Al-Ahram newspaper is one of Egypt’s oldest and most influential daily newspapers, widely regarded as a leading voice in the Arab media landscape.
  • 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_69ca84286fcc81909f6e7fd7a7e862a2 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4bace8488190a18c54e03be8410c completed April 1, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0e3ed7ffc819090f3706a8be4cbfa completed April 4, 2026, 10:11 a.m.
NEDg Description generation batch_69d0e502b68081909a9f9476421ba9b5 completed April 4, 2026, 10:16 a.m.
NED2 Entity disambiguation (via description) batch_69d0e5af7360819096c6295de0ce5f32 completed April 4, 2026, 10:19 a.m.
Created at: March 30, 2026, 7:40 p.m.