Triple

T10178801
Position Surface form Disambiguated ID Type / Status
Subject Mohmand Agency E235927 entity
Predicate tribe P1915 FINISHED
Object Safis
The Safis are a Pashtun tribal group historically associated with the Mohmand region along the Afghanistan–Pakistan border.
 E844887 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: Safis | Statement: [Mohmand Agency, tribe, Safis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Safis
Context triple: [Mohmand Agency, tribe, Safis]
  • A. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • B. Sijilmasa
    Sijilmasa was a medieval Moroccan oasis city that flourished as a key commercial hub linking North Africa with sub-Saharan gold and trade networks.
  • C. Sifayuan
    Sifayuan is the Mandarin name for Taiwan’s Judicial Yuan, the constitutional body responsible for overseeing the judiciary and interpreting the constitution.
  • D. Sikma
    Sikma is a surname most notably associated with Jack Sikma, a Hall of Fame American basketball player known for his successful NBA career with the Seattle SuperSonics.
  • E. Tsafiki
    Tsafiki is the indigenous language spoken by the Tsáchila people of Ecuador, belonging to the Barbacoan language family.
  • 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: Safis
Triple: [Mohmand Agency, tribe, Safis]
Generated description
The Safis are a Pashtun tribal group historically associated with the Mohmand region along the Afghanistan–Pakistan border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Safis
Target entity description: The Safis are a Pashtun tribal group historically associated with the Mohmand region along the Afghanistan–Pakistan border.
  • A. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • B. Sijilmasa
    Sijilmasa was a medieval Moroccan oasis city that flourished as a key commercial hub linking North Africa with sub-Saharan gold and trade networks.
  • C. Sifayuan
    Sifayuan is the Mandarin name for Taiwan’s Judicial Yuan, the constitutional body responsible for overseeing the judiciary and interpreting the constitution.
  • D. Sikma
    Sikma is a surname most notably associated with Jack Sikma, a Hall of Fame American basketball player known for his successful NBA career with the Seattle SuperSonics.
  • E. Tsafiki
    Tsafiki is the indigenous language spoken by the Tsáchila people of Ecuador, belonging to the Barbacoan language family.
  • 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_69ca84d1d5f88190ab878a1021ecff68 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdecd620808190892c6e3074500280 completed April 2, 2026, 4:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3012d11488190a410d389034da887 completed April 6, 2026, 12:41 a.m.
NEDg Description generation batch_69d30256ee40819098569b37eb27d3d1 completed April 6, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69d302d248e08190b6b7bae9343b6f9a completed April 6, 2026, 12:48 a.m.
Created at: March 30, 2026, 9:11 p.m.