Triple

T7958438
Position Surface form Disambiguated ID Type / Status
Subject Karlani E184799 entity
Predicate hasTribe P32607 FINISHED
Object Safi
Safi is a Pashtun tribe associated with the Karlani tribal confederation in Afghanistan and Pakistan.
 E703989 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: Safi | Statement: [Karlani, hasTribe, Safi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Safi
Context triple: [Karlani, hasTribe, Safi]
  • A. Safi
    Safi is a historic Moroccan port city on the Atlantic coast known for its fishing industry, ceramics, and Portuguese-era fortifications.
  • B. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • C. Khaleja
    Khaleja is a 2010 Telugu-language action-comedy film starring Mahesh Babu and Anushka Shetty, known for its blend of humor, fantasy elements, and social commentary.
  • D. Shuafat
    Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
  • E. Nefza
    Nefza is a town in northwestern Tunisia known for its forests, lakes, and proximity to the Mediterranean coast within the Béja Governorate.
  • 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: Safi
Triple: [Karlani, hasTribe, Safi]
Generated description
Safi is a Pashtun tribe associated with the Karlani tribal confederation in Afghanistan and Pakistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Safi
Target entity description: Safi is a Pashtun tribe associated with the Karlani tribal confederation in Afghanistan and Pakistan.
  • A. Safi
    Safi is a historic Moroccan port city on the Atlantic coast known for its fishing industry, ceramics, and Portuguese-era fortifications.
  • B. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • C. Khaleja
    Khaleja is a 2010 Telugu-language action-comedy film starring Mahesh Babu and Anushka Shetty, known for its blend of humor, fantasy elements, and social commentary.
  • D. Shuafat
    Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
  • E. Nefza
    Nefza is a town in northwestern Tunisia known for its forests, lakes, and proximity to the Mediterranean coast within the Béja Governorate.
  • 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_69ca8293a2388190aace944d7ed9c0c0 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3b80050c81909b2db95ade495052 completed March 31, 2026, 3:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe07d31a881909e891fdd73c4467b completed March 31, 2026, 2:55 p.m.
NEDg Description generation batch_69cbe554dfd881909edf2c20a7035f17 completed March 31, 2026, 3:16 p.m.
NED2 Entity disambiguation (via description) batch_69cc3429f4148190981d30c3cc4c3c9a completed March 31, 2026, 8:52 p.m.
Created at: March 30, 2026, 5:11 p.m.