Triple
T499331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yalta Municipality |
E10364
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Massandra
Massandra is a resort settlement near Yalta in Crimea, best known for its historic winery and palace.
|
E66841
|
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: Massandra | Statement: [Yalta Municipality, contains, Massandra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Massandra Context triple: [Yalta Municipality, contains, Massandra]
-
A.
Paola
Paola is an Italian noblewoman who became Queen consort of Belgium as the wife of King Albert II.
-
B.
Soral
Soral is a small rural municipality in southwestern Switzerland, located in the canton of Geneva near the French border.
-
C.
Amada
Amada is an ancient Egyptian temple site in Lower Nubia, renowned for its well-preserved reliefs and inscriptions dating back to the 18th Dynasty.
-
D.
Mila
Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
-
E.
Helena
Helena, also known as Saint Helena, was the mother of Roman Emperor Constantine the Great and is traditionally credited with finding the True Cross and promoting Christianity within the Roman Empire.
- 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: Massandra Triple: [Yalta Municipality, contains, Massandra]
Generated description
Massandra is a resort settlement near Yalta in Crimea, best known for its historic winery and palace.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Massandra Target entity description: Massandra is a resort settlement near Yalta in Crimea, best known for its historic winery and palace.
-
A.
Paola
Paola is an Italian noblewoman who became Queen consort of Belgium as the wife of King Albert II.
-
B.
Soral
Soral is a small rural municipality in southwestern Switzerland, located in the canton of Geneva near the French border.
-
C.
Amada
Amada is an ancient Egyptian temple site in Lower Nubia, renowned for its well-preserved reliefs and inscriptions dating back to the 18th Dynasty.
-
D.
Mila
Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
-
E.
Helena
Helena is the capital city of the U.S. state of Montana, known for its historic gold rush origins and scenic location in the northern Rocky Mountains.
- 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_69a2e847df8481909239ec08ccf1e376 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f119b14c8190a5a6b119579c2682 |
completed | Feb. 28, 2026, 1:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4c02c26808190b3078fb04f34572c |
completed | March 1, 2026, 10:39 p.m. |
| NEDg | Description generation | batch_69a4c0b0868881909e28d253c2971618 |
completed | March 1, 2026, 10:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4c131bd8881909501843d85145979 |
completed | March 1, 2026, 10:44 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.