Triple

T13759828
Position Surface form Disambiguated ID Type / Status
Subject Alki E330573 entity
Predicate hasSpellingVariant P457 FINISHED
Object Al-ki
Al-ki is an alternative spelling of Alki, a neighborhood and beach area in West Seattle known for its waterfront views and recreational activities.
 E1060082 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: Al-ki | Statement: [Alki, hasSpellingVariant, Al-ki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Al-ki
Context triple: [Alki, hasSpellingVariant, Al-ki]
  • A. Kisi
    Kisi is an indigenous Georgian white grape variety from the Kakheti region, known for producing aromatic, full-bodied wines often made in traditional qvevri.
  • B. Kabiye
    Kabiye is a Gur language spoken primarily in northern Togo and recognized as one of the country's major national languages.
  • C. Alikiba
    Alikiba is a prominent Tanzanian singer, songwriter, and recording artist known for his influential role in East African Bongo Flava music.
  • D. Kiuic
    Kiuic is an ancient Maya archaeological site in Mexico’s Puuc hills, known for its well-preserved architecture and evidence of a sudden, unexplained abandonment.
  • E. Kuci
    Kuci is the historical name of Kuqa, an ancient oasis town and important Buddhist cultural center along the Silk Road in what is now Xinjiang, China.
  • 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: Al-ki
Triple: [Alki, hasSpellingVariant, Al-ki]
Generated description
Al-ki is an alternative spelling of Alki, a neighborhood and beach area in West Seattle known for its waterfront views and recreational activities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Al-ki
Target entity description: Al-ki is an alternative spelling of Alki, a neighborhood and beach area in West Seattle known for its waterfront views and recreational activities.
  • A. Kisi
    Kisi is an indigenous Georgian white grape variety from the Kakheti region, known for producing aromatic, full-bodied wines often made in traditional qvevri.
  • B. Kabiye
    Kabiye is a Gur language spoken primarily in northern Togo and recognized as one of the country's major national languages.
  • C. Alikiba
    Alikiba is a prominent Tanzanian singer, songwriter, and recording artist known for his influential role in East African Bongo Flava music.
  • D. Kiuic
    Kiuic is an ancient Maya archaeological site in Mexico’s Puuc hills, known for its well-preserved architecture and evidence of a sudden, unexplained abandonment.
  • E. Kuci
    Kuci is the historical name of Kuqa, an ancient oasis town and important Buddhist cultural center along the Silk Road in what is now Xinjiang, China.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0223ab9081909db05334860405e0 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a8606dbc8190b0f7c38583986141 completed May 3, 2026, 7:56 p.m.
NEDg Description generation batch_69f7ac4f847c8190ab8be535e5399c79 completed May 3, 2026, 8:13 p.m.
NED2 Entity disambiguation (via description) batch_69f7acdf70f8819092700c7b6b619d13 completed May 3, 2026, 8:15 p.m.
Created at: April 9, 2026, 10:09 p.m.