Triple

T14715992
Position Surface form Disambiguated ID Type / Status
Subject Koules Fortress E345679 entity
Predicate alsoKnownAs P39 FINISHED
Object Koules
Koules is a Venetian-era coastal fortress in Heraklion, Crete, that historically protected the city’s harbor and now serves as a prominent cultural and tourist landmark.
 E1116501 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: Koules | Statement: [Koules Fortress, alsoKnownAs, Koules]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koules
Context triple: [Koules Fortress, alsoKnownAs, Koules]
  • A. Olesko
    Olesko is a historic town in western Ukraine best known for its medieval castle, which served as the birthplace of Polish King John III Sobieski.
  • B. Kashmore
    Kashmore is a town in Pakistan’s Sindh province that serves as a regional hub near the Guddu Barrage on the Indus River.
  • C. Qualley
    Qualley is the surname of an American family best known for actress and model Margaret Qualley and her mother, actress Andie MacDowell.
  • D. Kole
    Kole is a music producer known for working on the album "Songs About Girls."
  • E. Kaiten
    Kaiten was a Japanese warship that took part in the late-19th-century Boshin War naval engagements, including the Battle of Hakodate.
  • 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: Koules
Triple: [Koules Fortress, alsoKnownAs, Koules]
Generated description
Koules is a Venetian-era coastal fortress in Heraklion, Crete, that historically protected the city’s harbor and now serves as a prominent cultural and tourist landmark.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koules
Target entity description: Koules is a Venetian-era coastal fortress in Heraklion, Crete, that historically protected the city’s harbor and now serves as a prominent cultural and tourist landmark.
  • A. Olesko
    Olesko is a historic town in western Ukraine best known for its medieval castle, which served as the birthplace of Polish King John III Sobieski.
  • B. Kashmore
    Kashmore is a town in Pakistan’s Sindh province that serves as a regional hub near the Guddu Barrage on the Indus River.
  • C. Qualley
    Qualley is the surname of an American family best known for actress and model Margaret Qualley and her mother, actress Andie MacDowell.
  • D. Kole
    Kole is a music producer known for working on the album "Songs About Girls."
  • E. Kaiten
    Kaiten was a Japanese warship that took part in the late-19th-century Boshin War naval engagements, including the Battle of Hakodate.
  • 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb98688f48190b2b19ce7aa06a6db completed April 14, 2026, 10:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf0913d6c8190886df4cd0a92aa80 completed May 8, 2026, 2:17 p.m.
NEDg Description generation batch_69fdf3f89f088190ab745bddcc99a36c completed May 8, 2026, 2:32 p.m.
NED2 Entity disambiguation (via description) batch_69fdf47f265c8190a5494dcc7baf00fa completed May 8, 2026, 2:34 p.m.
Created at: April 10, 2026, 1:29 a.m.