Triple
T13039532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandar people |
E327153
|
entity |
| Predicate | traditionalBoatType |
P22942
|
FINISHED |
| Object |
sandeq
Sandeq is a sleek, outrigger sailing canoe from West Sulawesi, Indonesia, renowned for its speed and central role in the seafaring culture of the Mandar people.
|
E1017175
|
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: sandeq | Statement: [Mandar people, traditionalBoatType, sandeq]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: sandeq Context triple: [Mandar people, traditionalBoatType, sandeq]
-
A.
Sandve
Sandve is a small coastal village in Karmøy municipality in Rogaland county, southwestern Norway.
-
B.
SEAQ
SEAQ (Stock Exchange Automated Quotations) was the London Stock Exchange’s electronic quote-driven trading system used primarily for smaller and less liquid securities.
-
C.
Saane
The Saane, also known as the Sarine, is a major river in western Switzerland that flows through the canton of Fribourg before joining the Aare.
-
D.
Sääse
Sääse is a residential subdistrict of the Mustamäe district in Tallinn, Estonia.
-
E.
Sabbia
Sabbia is an off-road-oriented driving mode in the Lamborghini Urus optimized for performance and stability on sand and loose surfaces.
- 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: sandeq Triple: [Mandar people, traditionalBoatType, sandeq]
Generated description
Sandeq is a sleek, outrigger sailing canoe from West Sulawesi, Indonesia, renowned for its speed and central role in the seafaring culture of the Mandar people.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: sandeq Target entity description: Sandeq is a sleek, outrigger sailing canoe from West Sulawesi, Indonesia, renowned for its speed and central role in the seafaring culture of the Mandar people.
-
A.
Sandve
Sandve is a small coastal village in Karmøy municipality in Rogaland county, southwestern Norway.
-
B.
SEAQ
SEAQ (Stock Exchange Automated Quotations) was the London Stock Exchange’s electronic quote-driven trading system used primarily for smaller and less liquid securities.
-
C.
Saane
The Saane, also known as the Sarine, is a major river in western Switzerland that flows through the canton of Fribourg before joining the Aare.
-
D.
Sääse
Sääse is a residential subdistrict of the Mustamäe district in Tallinn, Estonia.
-
E.
Sabbia
Sabbia is an off-road-oriented driving mode in the Lamborghini Urus optimized for performance and stability on sand and loose surfaces.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d9804d8e3081909584c93df099859a |
completed | April 10, 2026, 10:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbd2f6a481909fdd418e7ad3cc22 |
completed | May 3, 2026, 4:15 a.m. |
| NEDg | Description generation | batch_69f6cd0d21e08190855dcbee000fc25d |
completed | May 3, 2026, 4:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6ce6b220c8190b1f49a9b2bfce692 |
completed | May 3, 2026, 4:26 a.m. |
Created at: April 9, 2026, 8:55 p.m.