Triple

T23378988
Position Surface form Disambiguated ID Type / Status
Subject Moken E593684 entity
Predicate traditionalVessel P22942 FINISHED
Object kabang
Kabang is a traditional wooden boat used by the Moken sea nomads of Southeast Asia for living, traveling, and fishing.
 E1584732 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: kabang | Statement: [Moken, traditionalVessel, kabang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: kabang
Context triple: [Moken, traditionalVessel, kabang]
  • A. KAB
    KAB is the station code for Kaulbachplatz, a public transit stop in Nuremberg, Germany.
  • B. kaba gaida
    Kaba gaida is a traditional low-pitched Bulgarian bagpipe from the Rhodope Mountains, known for its deep, mellow sound and central role in regional folk music.
  • C. Kabinawa
    Kabinawa is a small settlement located on the atoll of Abemama in the island nation of Kiribati in the central Pacific Ocean.
  • D. kan
    Kan is a Mayan term meaning “snake” or “serpent,” often associated with divinity, power, and the feathered serpent deity in Mesoamerican cultures.
  • E. kan
    kan is the ISO 639-2 code for the Kannada language, a major Dravidian language spoken predominantly in the Indian state of Karnataka.
  • 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: kabang
Triple: [Moken, traditionalVessel, kabang]
Generated description
Kabang is a traditional wooden boat used by the Moken sea nomads of Southeast Asia for living, traveling, and fishing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: kabang
Target entity description: Kabang is a traditional wooden boat used by the Moken sea nomads of Southeast Asia for living, traveling, and fishing.
  • A. KAB
    KAB is the station code for Kaulbachplatz, a public transit stop in Nuremberg, Germany.
  • B. kaba gaida
    Kaba gaida is a traditional low-pitched Bulgarian bagpipe from the Rhodope Mountains, known for its deep, mellow sound and central role in regional folk music.
  • C. Kabinawa
    Kabinawa is a small settlement located on the atoll of Abemama in the island nation of Kiribati in the central Pacific Ocean.
  • D. kan
    Kan is a Mayan term meaning “snake” or “serpent,” often associated with divinity, power, and the feathered serpent deity in Mesoamerican cultures.
  • E. kan
    kan is the ISO 639-2 code for the Kannada language, a major Dravidian language spoken predominantly in the Indian state of Karnataka.
  • 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b5e4f0819081a5d4586796677b completed April 29, 2026, 6:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c5de3eecc8190be3899c9e3891c1c completed May 19, 2026, 12:56 p.m.
NEDg Description generation batch_6a0c61ecbf288190b8a8567e3f049b10 completed May 19, 2026, 1:13 p.m.
NED2 Entity disambiguation (via description) batch_6a0c624ac9b88190aa025df3744b7f8a completed May 19, 2026, 1:14 p.m.
Created at: April 17, 2026, 5:33 p.m.