Triple
T6613462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madeira wine |
E149290
|
entity |
| Predicate | grapeVarietyUsed |
P975
|
FINISHED |
| Object |
Bual
Bual is a white Portuguese grape variety traditionally used to produce medium-rich, nutty and caramel-toned styles of Madeira wine.
|
E607802
|
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: Bual | Statement: [Madeira wine, grapeVarietyUsed, Bual]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bual Context triple: [Madeira wine, grapeVarietyUsed, Bual]
-
A.
Bua
Bua is a province on the island of Vanua Levu in Fiji, known for its rural communities and largely undeveloped natural landscapes.
-
B.
Tambolaka
Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
-
C.
Boengkoe
Boengkoe is an alternative name for the Bungku language, an Austronesian language spoken in Southeast Sulawesi, Indonesia.
-
D.
Bislig
Bislig is a coastal city in the Caraga region of Mindanao in the Philippines, known for its proximity to the Tinuy-an Falls and its history as a former major paper-mill town.
-
E.
Tagbanwa
Tagbanwa is an indigenous Philippine script historically used by the Tagbanwa people of Palawan for writing their Austronesian language.
- 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: Bual Triple: [Madeira wine, grapeVarietyUsed, Bual]
Generated description
Bual is a white Portuguese grape variety traditionally used to produce medium-rich, nutty and caramel-toned styles of Madeira wine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bual Target entity description: Bual is a white Portuguese grape variety traditionally used to produce medium-rich, nutty and caramel-toned styles of Madeira wine.
-
A.
Bua
Bua is a province on the island of Vanua Levu in Fiji, known for its rural communities and largely undeveloped natural landscapes.
-
B.
Tambolaka
Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
-
C.
Boengkoe
Boengkoe is an alternative name for the Bungku language, an Austronesian language spoken in Southeast Sulawesi, Indonesia.
-
D.
Bislig
Bislig is a coastal city in the Caraga region of Mindanao in the Philippines, known for its proximity to the Tinuy-an Falls and its history as a former major paper-mill town.
-
E.
Tagbanwa
Tagbanwa is an indigenous Philippine script historically used by the Tagbanwa people of Palawan for writing their Austronesian language.
- 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_69c687ebc680819094caf71faba2efe2 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6af3890408190a0edf2f813b93196 |
completed | March 27, 2026, 4:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6e44154a08190b031bb74624fba1e |
completed | March 27, 2026, 8:10 p.m. |
| NEDg | Description generation | batch_69c6e61218c4819084c170611077f0e6 |
completed | March 27, 2026, 8:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c6e7cc21548190b302e2e31f9cadd0 |
completed | March 27, 2026, 8:25 p.m. |
Created at: March 27, 2026, 1:57 p.m.