Triple

T13405474
Position Surface form Disambiguated ID Type / Status
Subject DAI Amman Office E319944 entity
Predicate regionServed P82 FINISHED
Object Jordan
Jordan is a Middle Eastern country known for its rich historical sites, including Petra and the Dead Sea, and its role as a relatively stable nation in a turbulent region.
E11658 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: Jordan | Statement: [DAI Amman Office, regionServed, Jordan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jordan
Context triple: [DAI Amman Office, regionServed, Jordan]
  • A. Jordan
    Jordan is a municipality in the Philippines that serves as the capital of the island province of Guimaras in the Western Visayas region.
  • B. Jordan
    Jordan was a Formula One racing team and constructor known for launching the careers of several top drivers and competing in the sport during the 1990s and early 2000s.
  • C. Jordan
    Jordan is a scientist known for formally describing the bacterial genus Bradyrhizobium.
  • D. Jordan
    Jordan is a small community in the town of Lincoln, Ontario, known for its wineries, fruit farms, and scenic location on the Niagara Peninsula.
  • E. Jordan
    "Jordan" is a song featured on Emmylou Harris's bluegrass-influenced album "Roses in the Snow."
  • 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: Jordan
Triple: [DAI Amman Office, regionServed, Jordan]
Generated description
Jordan is a Middle Eastern country known for its rich historical sites, including Petra and the Dead Sea, and its role as a relatively stable nation in a turbulent region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jordan
Target entity description: Jordan is a Middle Eastern country known for its rich historical sites, including Petra and the Dead Sea, and its role as a relatively stable nation in a turbulent region.
  • A. Jordan chosen
    Jordan is a Middle Eastern country located at the crossroads of Asia, Africa, and Europe, known for its ancient archaeological sites like Petra and its strategic political role in the region.
  • B. Jordan
    Jordan is a common given name used by people of all genders in many English-speaking and other countries.
  • C. Jordan
    Jordan is a municipality in the Philippines that serves as the capital of the island province of Guimaras in the Western Visayas region.
  • D. Jordan
    Jordan is a small community in the town of Lincoln, Ontario, known for its wineries, fruit farms, and scenic location on the Niagara Peninsula.
  • E. Jordan
    Jordan is a busy urban area in Kowloon, Hong Kong, known for its dense mix of residential buildings, shops, and traditional eateries.
  • F. None of above.

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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbae4be498819094798473a1bfd853 completed April 12, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7307904608190ad647f741c08dc42 completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f731d83ca081909ff0762c01280993 completed May 3, 2026, 11:30 a.m.
NED2 Entity disambiguation (via description) batch_69f7324625288190bed99890ba021e46 completed May 3, 2026, 11:32 a.m.
Created at: April 9, 2026, 9:34 p.m.