Triple

T5386123
Position Surface form Disambiguated ID Type / Status
Subject Sogdians E120202 entity
Predicate ethnicSuccessor P62943 FINISHED
Object Tajiks E22451 NE FINISHED

How this triple was built (3 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: Tajiks | Statement: [Sogdians, ethnicSuccessor, Tajiks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tajiks
Context triple: [Sogdians, ethnicSuccessor, Tajiks]
  • A. Tajiks chosen
    Tajiks are an Iranian ethnic group of Central Asia, primarily inhabiting Tajikistan and parts of Afghanistan and Uzbekistan, known for their Persian cultural and linguistic heritage.
  • B. Uzbeks
    Uzbeks are a Turkic ethnic group of Central Asia, primarily associated with Uzbekistan but also forming significant communities in neighboring countries such as Afghanistan.
  • C. Usbek
    Usbek is a Persian nobleman and one of the central letter-writing protagonists in Montesquieu’s satirical epistolary novel "Persian Letters," through whose observations European society is critically examined.
  • D. Tajikistan
    Tajikistan is a landlocked, mountainous country in Central Asia known for its rugged Pamir range and as a former Soviet republic with an economy centered on agriculture, hydropower, and remittances.
  • E. Turkmens
    Turkmens are a Turkic ethnic group primarily inhabiting Turkmenistan and surrounding regions, known for their shared linguistic and cultural heritage with other Oghuz Turkic peoples.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ethnicSuccessor
Context triple: [Sogdians, ethnicSuccessor, Tajiks]
  • A. laterAdministrativeSuccessor
    Indicates that one administrative entity succeeds another in governing authority or jurisdiction at a later time.
  • B. deFactoSuccessor
    Indicates that one entity has effectively taken over the role, function, or position of another, even if not formally or legally recognized as its successor.
  • C. successorInHouse
    Indicates that one entity directly follows another in holding a position or role within the same house or lineage.
  • D. countrySuccessor
    Indicates that one country is the direct successor state to another, inheriting its sovereignty or international status.
  • E. successorNamesake
    Indicates that one entity is named after another entity that precedes it, typically as its successor or continuation in name.
  • 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_69bd46354c648190a38b26f107010a96 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd86f6f39c8190aa6af12370e3d12b completed March 20, 2026, 5:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf335b5acc81908c43776b614e9c1a completed March 22, 2026, 12:10 a.m.
PD Predicate disambiguation batch_69bd8463a9c88190bd760378f3026180 completed March 20, 2026, 5:31 p.m.
PDg Predicate description generation batch_69bd853005088190b1b092a9beb090b2 completed March 20, 2026, 5:34 p.m.
Created at: March 20, 2026, 2:03 p.m.