Triple
T20834492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comorian language |
E512921
|
entity |
| Predicate | hasEndonym |
P1435
|
FINISHED |
| Object |
Shikomoro
Shikomoro is the native Bantu language spoken in the Comoros, heavily influenced by Arabic and French.
|
E1540922
|
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: Shikomoro | Statement: [Comorian language, hasEndonym, Shikomoro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shikomoro Context triple: [Comorian language, hasEndonym, Shikomoro]
-
A.
Tsuchiyama
Tsuchiyama is a locality in Japan known as an access point for hiking routes up Mount Atago.
-
B.
Mizugakiyama
Mizugakiyama is one of the prominent rocky peaks of Japan’s Mount Myogi, known for its dramatic cliffs and popular hiking and climbing routes.
-
C.
Sakizaya
The Sakizaya are an indigenous ethnic group of Taiwan with their own distinct language, culture, and traditions, officially recognized by the Taiwanese government.
-
D.
Wakakusa-yama
Wakakusa-yama is a grass-covered hill in Nara, Japan, known for its panoramic views and the annual Yamayaki fire festival in which its slopes are set ablaze.
-
E.
Kurodake
Kurodake is a prominent mountain in Japan’s Daisetsuzan range, known for its hiking, alpine scenery, and access via ropeway and chairlift.
- 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: Shikomoro Triple: [Comorian language, hasEndonym, Shikomoro]
Generated description
Shikomoro is the native Bantu language spoken in the Comoros, heavily influenced by Arabic and French.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Shikomoro Target entity description: Shikomoro is the native Bantu language spoken in the Comoros, heavily influenced by Arabic and French.
-
A.
Tsuchiyama
Tsuchiyama is a locality in Japan known as an access point for hiking routes up Mount Atago.
-
B.
Mizugakiyama
Mizugakiyama is one of the prominent rocky peaks of Japan’s Mount Myogi, known for its dramatic cliffs and popular hiking and climbing routes.
-
C.
Sakizaya
The Sakizaya are an indigenous ethnic group of Taiwan with their own distinct language, culture, and traditions, officially recognized by the Taiwanese government.
-
D.
Wakakusa-yama
Wakakusa-yama is a grass-covered hill in Nara, Japan, known for its panoramic views and the annual Yamayaki fire festival in which its slopes are set ablaze.
-
E.
Kurodake
Kurodake is a prominent mountain in Japan’s Daisetsuzan range, known for its hiking, alpine scenery, and access via ropeway and chairlift.
- 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_69e0b4cf62a88190bbf92351e9e57259 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c32554648190bd66ac99b3a9072b |
completed | April 21, 2026, 12:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b17c7198c8190b96754a4a0b317c1 |
completed | May 18, 2026, 1:44 p.m. |
| NEDg | Description generation | batch_6a0b1ac642408190bb265ec0a797daf2 |
completed | May 18, 2026, 1:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b1b28377c8190a6c28b470ee5f1f8 |
completed | May 18, 2026, 1:59 p.m. |
Created at: April 16, 2026, 12:42 p.m.