Triple
T8535372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tushpa |
E202064
|
entity |
| Predicate | locatedOnShoreOf |
P969
|
FINISHED |
| Object | Lake Van |
E193071
|
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: Lake Van | Statement: [Tushpa, locatedOnShoreOf, Lake Van]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Van Context triple: [Tushpa, locatedOnShoreOf, Lake Van]
-
A.
Lake Van
chosen
Lake Van is the largest lake in Turkey, a saline endorheic lake renowned for its high altitude, unique ecosystem, and historical Armenian cultural sites along its shores.
-
B.
Lake Tuz
Lake Tuz is a large, shallow hypersaline lake in central Turkey known for its extensive salt flats and ecological importance as a habitat for migratory birds.
-
C.
Lake Çıldır
Lake Çıldır is a large high-altitude freshwater lake in northeastern Turkey, known for its scenic beauty, fishing, and winter ice activities.
-
D.
Lake Orta
Lake Orta is a picturesque glacial lake in northern Italy, renowned for its tranquil atmosphere, historic lakeside villages, and the island of San Giulio.
-
E.
Lake Sevan
Lake Sevan is a large high-altitude freshwater lake in eastern Armenia, renowned as one of the country’s most important natural and cultural landmarks.
- 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a295c88190a432a060ee73f04e |
completed | March 31, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cecc6239a48190b8b4370341ec62c5 |
completed | April 2, 2026, 8:06 p.m. |
Created at: March 30, 2026, 6:17 p.m.