Triple
T8575080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinamalé Bridge |
E203027
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Malé |
E159965
|
NE FINISHED |
How this triple was built (2 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: Malé | Statement: [Sinamalé Bridge, connects, Malé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Malé Context triple: [Sinamalé Bridge, connects, Malé]
-
A.
Malé
chosen
Malé is the densely populated island city that serves as the political, economic, and cultural center of the Maldives.
-
B.
Maléter
Maléter is the surname of Pál Maléter, a Hungarian military officer and key figure in the 1956 Hungarian Revolution.
-
C.
Malo
Malo is an Oceanic language of Vanuatu, also known as Tamambo, spoken primarily on Malo Island.
-
D.
Malé City
Malé City is the densely populated capital of the Maldives, serving as its political, economic, and cultural center in the Indian Ocean.
-
E.
Kleine Enz
Kleine Enz is a small river in Baden-Württemberg, Germany, that serves as a tributary of the Enz.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8328ebe481909a8c038fa79959b4 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbea947f188190af469babaa73ddf6 |
completed | March 31, 2026, 3:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd069faa481908db58399fe8f72f1 |
completed | April 3, 2026, 2:36 p.m. |
Created at: March 30, 2026, 6:21 p.m.