Triple

T22111644
Position Surface form Disambiguated ID Type / Status
Subject Senneh knot E546431 entity
Predicate alsoKnownAs P39 FINISHED
Object Farsibaff
Farsibaff is another name for the Senneh knot, a fine and tightly woven asymmetrical knot commonly used in traditional Persian carpet weaving.
 E1519647 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: Farsibaff | Statement: [Senneh knot, alsoKnownAs, Farsibaff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Farsibaff
Context triple: [Senneh knot, alsoKnownAs, Farsibaff]
  • A. Farap
    Farap is a town in eastern Turkmenistan that serves as an important border crossing and transport hub between Turkmenistan and Uzbekistan.
  • B. Farraaj
    Farraaj is a British-trained Thoroughbred racehorse best known for winning the 2012 Winter Derby and placing in several other major middle-distance races.
  • C. Furttal
    Furttal is a small valley region in the canton of Zurich, Switzerland, known for its suburban communities and proximity to the city of Zurich.
  • D. Saffig
    Saffig is a small municipality in the district of Mayen-Koblenz in the German state of Rhineland-Palatinate.
  • E. Falbalas
    Falbalas is a 1945 French romantic drama film by Jacques Becker, celebrated for its stylish depiction of the Paris fashion world and featuring Micheline Presle in a leading role.
  • 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: Farsibaff
Triple: [Senneh knot, alsoKnownAs, Farsibaff]
Generated description
Farsibaff is another name for the Senneh knot, a fine and tightly woven asymmetrical knot commonly used in traditional Persian carpet weaving.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Farsibaff
Target entity description: Farsibaff is another name for the Senneh knot, a fine and tightly woven asymmetrical knot commonly used in traditional Persian carpet weaving.
  • A. Farap
    Farap is a town in eastern Turkmenistan that serves as an important border crossing and transport hub between Turkmenistan and Uzbekistan.
  • B. Farraaj
    Farraaj is a British-trained Thoroughbred racehorse best known for winning the 2012 Winter Derby and placing in several other major middle-distance races.
  • C. Furttal
    Furttal is a small valley region in the canton of Zurich, Switzerland, known for its suburban communities and proximity to the city of Zurich.
  • D. Saffig
    Saffig is a small municipality in the district of Mayen-Koblenz in the German state of Rhineland-Palatinate.
  • E. Falbalas
    Falbalas is a 1945 French romantic drama film by Jacques Becker, celebrated for its stylish depiction of the Paris fashion world and featuring Micheline Presle in a leading role.
  • 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12949cc7881908898ca7dc130f57f completed April 28, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a8f175d2c819096d4a128307f2f67 completed May 18, 2026, 4:01 a.m.
NEDg Description generation batch_6a0a90ca49c48190b01c88ae7e841cb4 completed May 18, 2026, 4:08 a.m.
NED2 Entity disambiguation (via description) batch_6a0a915bd5748190afc5a5a6e9398564 completed May 18, 2026, 4:11 a.m.
Created at: April 16, 2026, 8:31 p.m.