Triple

T10181494
Position Surface form Disambiguated ID Type / Status
Subject Kirkuk E236794 entity
Predicate historicalName P65 FINISHED
Object Karkha D-Bet Slokh
Karkha D-Bet Slokh is an ancient name of the city now known as Kirkuk, a historically significant urban center in northern Iraq.
E845745 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: Karkha D-Bet Slokh | Statement: [Kirkuk, historicalName, Karkha D-Bet Slokh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karkha D-Bet Slokh
Context triple: [Kirkuk, historicalName, Karkha D-Bet Slokh]
  • A. Chakari
    Chakari is a small mining and agricultural town located in the Mashonaland West Province of Zimbabwe.
  • B. Kallar Kahar
    Kallar Kahar is a town in Pakistan’s Punjab province known for its scenic lake, historic Mughal-era garden, and location along the M2 Motorway.
  • C. Kasarvadavali
    Kasarvadavali is a rapidly developing residential and commercial locality situated along Ghodbunder Road in Thane, Maharashtra, India.
  • D. Shaviklde
    Shaviklde is a prominent mountain peak in Georgia known as the highest summit of the Trialeti Range.
  • E. Dadu’a
    Dadu’a is an indigenous local language spoken on Atauro Island, part of Timor-Leste.
  • 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: Karkha D-Bet Slokh
Triple: [Kirkuk, historicalName, Karkha D-Bet Slokh]
Generated description
Karkha D-Bet Slokh is an ancient name of the city now known as Kirkuk, a historically significant urban center in northern Iraq.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karkha D-Bet Slokh
Target entity description: Karkha D-Bet Slokh is an ancient name of the city now known as Kirkuk, a historically significant urban center in northern Iraq.
  • A. Chakari
    Chakari is a small mining and agricultural town located in the Mashonaland West Province of Zimbabwe.
  • B. Kallar Kahar
    Kallar Kahar is a town in Pakistan’s Punjab province known for its scenic lake, historic Mughal-era garden, and location along the M2 Motorway.
  • C. Kasarvadavali
    Kasarvadavali is a rapidly developing residential and commercial locality situated along Ghodbunder Road in Thane, Maharashtra, India.
  • D. Shaviklde
    Shaviklde is a prominent mountain peak in Georgia known as the highest summit of the Trialeti Range.
  • E. Dadu’a
    Dadu’a is an indigenous local language spoken on Atauro Island, part of Timor-Leste.
  • 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_69ca84d7260c8190bfbec36762943f37 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cded32b91c8190b01ad37b2456080a completed April 2, 2026, 4:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3013f0c54819092ee9c2c46fdf69e completed April 6, 2026, 12:41 a.m.
NEDg Description generation batch_69d3028a4384819094a7daef7287e54f completed April 6, 2026, 12:47 a.m.
NED2 Entity disambiguation (via description) batch_69d302e9d2688190bc292f8f2287c458 completed April 6, 2026, 12:48 a.m.
Created at: March 30, 2026, 9:11 p.m.