Triple

T11707938
Position Surface form Disambiguated ID Type / Status
Subject Assos E278295 entity
Predicate alsoKnownAs P39 FINISHED
Object Behram
Behram is an alternative name for the ancient Greek city of Assos, a historic coastal settlement in present-day Turkey known for its classical ruins and scenic Aegean setting.
E942547 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: Behram | Statement: [Assos, alsoKnownAs, Behram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Behram
Context triple: [Assos, alsoKnownAs, Behram]
  • A. Khusrav
    Khusrav is a masculine given name of Persian origin, historically borne by princes and notable figures in Central and South Asia.
  • B. Shapurji
    Shapurji is the given name of Shapurji Saklatvala, a prominent early 20th-century British Communist politician of Indian Parsi origin.
  • C. Aram Shah
    Aram Shah was a short-reigning early ruler of the Delhi Sultanate who briefly succeeded Qutb al-Din Aibak before being overthrown by Iltutmish.
  • D. Fereydun
    Fereydun is a legendary hero and king in Persian mythology, best known from the Shahnameh for overthrowing the tyrant Zahhak and ushering in a just reign.
  • E. Goshtasp
    Goshtasp is a legendary Kayanian king in Persian mythology, best known as the father of the hero Esfandiyar and a patron of Zoroaster.
  • 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: Behram
Triple: [Assos, alsoKnownAs, Behram]
Generated description
Behram is an alternative name for the ancient Greek city of Assos, a historic coastal settlement in present-day Turkey known for its classical ruins and scenic Aegean setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Behram
Target entity description: Behram is an alternative name for the ancient Greek city of Assos, a historic coastal settlement in present-day Turkey known for its classical ruins and scenic Aegean setting.
  • A. Khusrav
    Khusrav is a masculine given name of Persian origin, historically borne by princes and notable figures in Central and South Asia.
  • B. Shapurji
    Shapurji is the given name of Shapurji Saklatvala, a prominent early 20th-century British Communist politician of Indian Parsi origin.
  • C. Aram Shah
    Aram Shah was a short-reigning early ruler of the Delhi Sultanate who briefly succeeded Qutb al-Din Aibak before being overthrown by Iltutmish.
  • D. Fereydun
    Fereydun is a legendary hero and king in Persian mythology, best known from the Shahnameh for overthrowing the tyrant Zahhak and ushering in a just reign.
  • E. Goshtasp
    Goshtasp is a legendary Kayanian king in Persian mythology, best known as the father of the hero Esfandiyar and a patron of Zoroaster.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a49de0388190a063739426bf90e8 completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef836388bc8190827ce4af609d8b61 completed April 27, 2026, 3:40 p.m.
NEDg Description generation batch_69ef96b0169081909ad5c5d40a006e64 completed April 27, 2026, 5:02 p.m.
NED2 Entity disambiguation (via description) batch_69efb4dad6a481909a54511b6233993b completed April 27, 2026, 7:11 p.m.
Created at: April 8, 2026, 9:40 p.m.