Triple

T8946005
Position Surface form Disambiguated ID Type / Status
Subject Alexandros E213222 entity
Predicate hasVariant P455 FINISHED
Object Iskandar E38043 NE FINISHED

How this triple was built (2 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: Iskandar | Statement: [Alexandros, hasVariant, Iskandar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iskandar
Context triple: [Alexandros, hasVariant, Iskandar]
  • A. Eskandar chosen
    Eskandar is a Persian and Arabic form of the name Alexander, commonly used in historical and literary contexts to refer to Alexander the Great.
  • B. Sulayman
    Sulayman is the Islamic name for King Solomon, a prophet and wise monarch revered in Abrahamic traditions for his justice, wisdom, and leadership.
  • C. Kujula Kadphises
    Kujula Kadphises was the founding ruler of the Kushan Empire, known for unifying various Yuezhi tribes and establishing a powerful kingdom in Bactria and northwestern India in the 1st century CE.
  • D. Sulaiman
    Sulaiman is a musical artist known for contributing featured vocals to tracks such as "10 Day."
  • E. King Shahdov
    King Shahdov is the exiled monarch and central figure of Charlie Chaplin’s satirical film "A King in New York," through whom the movie critiques American politics, media, and McCarthy-era paranoia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66dd00c481908ff20fd66c1954cc completed April 1, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc1fcb44481908324220aeba1f4e2 completed April 3, 2026, 1:34 p.m.
Created at: March 30, 2026, 6:59 p.m.