Triple

T1761806
Position Surface form Disambiguated ID Type / Status
Subject Latium E38673 entity
Predicate contains P35 FINISHED
Object Tibur
Tibur is the ancient Roman town in Latium, now known as Tivoli, famed for its villas and temples east of Rome.
E199555 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: Tibur | Statement: [Latium, contains, Tibur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tibur
Context triple: [Latium, contains, Tibur]
  • A. Tain
    Tain is a historic town in the Highlands of Scotland, known as one of the country’s oldest royal burghs and a regional administrative and judicial center.
  • B. Timanfaya
    Timanfaya is a dramatic volcanic landscape and national park on the Spanish island of Lanzarote, renowned for its otherworldly lava fields and geothermal activity.
  • C. Val-Kill
    Val-Kill is the Hyde Park, New York retreat that served as Eleanor Roosevelt’s personal home and later became a national historic site honoring her life and work.
  • D. Powisle
    Powiśle is a historical region in northern Poland situated along the Vistula River, known for its cultural heritage and picturesque landscapes.
  • E. The Turim
    The Turim is a foundational 14th-century Jewish legal code by Rabbi Jacob ben Asher that systematically organizes halakhic rulings into four major sections.
  • 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: Tibur
Triple: [Latium, contains, Tibur]
Generated description
Tibur is the ancient Roman town in Latium, now known as Tivoli, famed for its villas and temples east of Rome.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tibur
Target entity description: Tibur is the ancient Roman town in Latium, now known as Tivoli, famed for its villas and temples east of Rome.
  • A. Tain
    Tain is a historic town in the Highlands of Scotland, known as one of the country’s oldest royal burghs and a regional administrative and judicial center.
  • B. Timanfaya
    Timanfaya is a dramatic volcanic landscape and national park on the Spanish island of Lanzarote, renowned for its otherworldly lava fields and geothermal activity.
  • C. Val-Kill
    Val-Kill is the Hyde Park, New York retreat that served as Eleanor Roosevelt’s personal home and later became a national historic site honoring her life and work.
  • D. Powisle
    Powiśle is a historical region in northern Poland situated along the Vistula River, known for its cultural heritage and picturesque landscapes.
  • E. The Turim
    The Turim is a foundational 14th-century Jewish legal code by Rabbi Jacob ben Asher that systematically organizes halakhic rulings into four major sections.
  • 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_69a8862d562481908d7025a1c1f67c0d completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa6463ac0081909e9ebe6ebf1db857 completed March 6, 2026, 5:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada98eb0348190a44e05393a2c6eff completed March 8, 2026, 4:53 p.m.
NEDg Description generation batch_69adae9845f081908904030f7a10df63 completed March 8, 2026, 5:15 p.m.
NED2 Entity disambiguation (via description) batch_69adafa3494c8190b34a6930cf38ca40 completed March 8, 2026, 5:19 p.m.
Created at: March 4, 2026, 7:31 p.m.