Triple

T14348551
Position Surface form Disambiguated ID Type / Status
Subject Karak E355791 entity
Predicate hasAlternativeName P39 FINISHED
Object Al-Karak
Al-Karak is a historic Jordanian city best known for its imposing Crusader-era hilltop castle overlooking the surrounding region.
E1094645 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: Al-Karak | Statement: [Karak, hasAlternativeName, Al-Karak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Al-Karak
Context triple: [Karak, hasAlternativeName, Al-Karak]
  • A. Qalqilya
    Qalqilya is a Palestinian city in the northwestern West Bank, known for being almost completely encircled by the Israeli West Bank barrier.
  • B. Bayt Hanun
    Bayt Hanun is a town in the northeastern Gaza Strip, near the border with Israel, known for its strategic location and frequent involvement in the Israeli–Palestinian conflict.
  • C. Ramla
    Ramla is an Israeli city historically significant as a major religious and communal center for Karaite Jews.
  • D. Beit Lahia
    Beit Lahia is a town in the northern Gaza Strip known for its agricultural lands and proximity to several major refugee camps.
  • E. Ma’an
    Ma’an is a major city in southern Jordan that serves as an important regional hub and gateway to nearby desert and archaeological sites.
  • 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: Al-Karak
Triple: [Karak, hasAlternativeName, Al-Karak]
Generated description
Al-Karak is a historic Jordanian city best known for its imposing Crusader-era hilltop castle overlooking the surrounding region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Al-Karak
Target entity description: Al-Karak is a historic Jordanian city best known for its imposing Crusader-era hilltop castle overlooking the surrounding region.
  • A. Qalqilya
    Qalqilya is a Palestinian city in the northwestern West Bank, known for being almost completely encircled by the Israeli West Bank barrier.
  • B. Bayt Hanun
    Bayt Hanun is a town in the northeastern Gaza Strip, near the border with Israel, known for its strategic location and frequent involvement in the Israeli–Palestinian conflict.
  • C. Ramla
    Ramla is an Israeli city historically significant as a major religious and communal center for Karaite Jews.
  • D. Beit Lahia
    Beit Lahia is a town in the northern Gaza Strip known for its agricultural lands and proximity to several major refugee camps.
  • E. Ma’an
    Ma’an is a major city in southern Jordan that serves as an important regional hub and gateway to nearby desert and archaeological sites.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8e8d081c8190ac805726a3e98f4c completed April 14, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c4145c081909832e2334a064fb0 completed May 8, 2026, 2:36 a.m.
NEDg Description generation batch_69fd4d1415908190a04713f504491387 completed May 8, 2026, 2:40 a.m.
NED2 Entity disambiguation (via description) batch_69fd4da8af2c8190ad3e78bbe1c9cd7a completed May 8, 2026, 2:42 a.m.
Created at: April 10, 2026, 1:14 a.m.