Triple
T3515316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torres Strait Islanders |
E74291
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object |
Brokan
Brokan is a creole language spoken by Torres Strait Islanders in northern Australia.
|
E365532
|
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: Brokan | Statement: [Torres Strait Islanders, hasLanguage, Brokan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brokan Context triple: [Torres Strait Islanders, hasLanguage, Brokan]
-
A.
Mount Klabat
Mount Klabat is a stratovolcano and the highest peak in North Sulawesi, Indonesia, known for its crater lake and popular hiking routes.
-
B.
Mount Eisen
Mount Eisen is a peak in California’s Sierra Nevada range, situated along the rugged Great Western Divide within Sequoia National Park.
-
C.
Hoche
Hoche is a Paris Métro station located in the northeastern suburb of Pantin, serving as a stop on the city’s Line 5.
-
D.
Brocken
Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
-
E.
Mount Egon
Mount Egon is an active stratovolcano located on the island of Flores in Indonesia, known for its periodic eruptions and geothermal activity.
- 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: Brokan Triple: [Torres Strait Islanders, hasLanguage, Brokan]
Generated description
Brokan is a creole language spoken by Torres Strait Islanders in northern Australia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brokan Target entity description: Brokan is a creole language spoken by Torres Strait Islanders in northern Australia.
-
A.
Mount Klabat
Mount Klabat is a stratovolcano and the highest peak in North Sulawesi, Indonesia, known for its crater lake and popular hiking routes.
-
B.
Mount Eisen
Mount Eisen is a peak in California’s Sierra Nevada range, situated along the rugged Great Western Divide within Sequoia National Park.
-
C.
Hoche
Hoche is a Paris Métro station located in the northeastern suburb of Pantin, serving as a stop on the city’s Line 5.
-
D.
Brocken
Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
-
E.
Mount Egon
Mount Egon is an active stratovolcano located on the island of Flores in Indonesia, known for its periodic eruptions and geothermal activity.
- 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_69ad85cfb5c881909c9a2edd9d6043cc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc30362c81908ca7497a6a935cc6 |
completed | March 8, 2026, 6:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b37e7a5ab08190971c9dfd6550eb2d |
completed | March 13, 2026, 3:03 a.m. |
| NEDg | Description generation | batch_69b37ff7b1c8819085b16ea9eb9175eb |
completed | March 13, 2026, 3:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b3808903e481908d312766e126204f |
completed | March 13, 2026, 3:12 a.m. |
Created at: March 8, 2026, 3:19 p.m.