Triple

T9009961
Position Surface form Disambiguated ID Type / Status
Subject Nimrud E215442 entity
Predicate alsoKnownAs P39 FINISHED
Object Calah
Calah is an ancient Assyrian city, better known today as Nimrud, which served as a major political and cultural center of the Neo-Assyrian Empire in northern Mesopotamia.
E771653 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: Calah | Statement: [Nimrud, alsoKnownAs, Calah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calah
Context triple: [Nimrud, alsoKnownAs, Calah]
  • A. Cumae
    Cumae was an ancient Greek colony in Italy, renowned as one of the earliest Hellenic settlements in the West and famous for its oracle, the Cumaean Sibyl.
  • B. Naachtún
    Naachtún is an ancient Maya archaeological site in northern Guatemala known for its remote jungle location and extensive ruins of a major Classic-period city.
  • C. Kulun
    Kulun is an alternative name for the Kulon language, a lesser-known Papuan language spoken in parts of Indonesia.
  • D. Seibal
    Seibal is an ancient Maya archaeological site in Guatemala known for its well-preserved stelae and strategic location along the Usumacinta River.
  • E. Degahabur
    Degahabur is a town in eastern Ethiopia that serves as an administrative and commercial center within the Somali Region.
  • 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: Calah
Triple: [Nimrud, alsoKnownAs, Calah]
Generated description
Calah is an ancient Assyrian city, better known today as Nimrud, which served as a major political and cultural center of the Neo-Assyrian Empire in northern Mesopotamia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Calah
Target entity description: Calah is an ancient Assyrian city, better known today as Nimrud, which served as a major political and cultural center of the Neo-Assyrian Empire in northern Mesopotamia.
  • A. Cumae
    Cumae was an ancient Greek colony in Italy, renowned as one of the earliest Hellenic settlements in the West and famous for its oracle, the Cumaean Sibyl.
  • B. Naachtún
    Naachtún is an ancient Maya archaeological site in northern Guatemala known for its remote jungle location and extensive ruins of a major Classic-period city.
  • C. Kulun
    Kulun is an alternative name for the Kulon language, a lesser-known Papuan language spoken in parts of Indonesia.
  • D. Seibal
    Seibal is an ancient Maya archaeological site in Guatemala known for its well-preserved stelae and strategic location along the Usumacinta River.
  • E. Degahabur
    Degahabur is a town in eastern Ethiopia that serves as an administrative and commercial center within the Somali Region.
  • 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_69ca83a2bf088190986ee7a8eb90407d completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc69c00ae8819090786385a72e8baf completed April 1, 2026, 12:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0ee18b48190a520ce4e1d3a41ef completed April 3, 2026, 2:38 p.m.
NEDg Description generation batch_69cfd14a28d48190b63561f9a537daeb completed April 3, 2026, 2:40 p.m.
NED2 Entity disambiguation (via description) batch_69cfd1fd6db08190921285c3cfd3ce91 completed April 3, 2026, 2:43 p.m.
Created at: March 30, 2026, 7:06 p.m.