Triple
T15827485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CEC Palace |
E383780
|
entity |
| Predicate | client |
P27
|
FINISHED |
| Object |
CEC Bank
CEC Bank is one of Romania’s oldest state-owned financial institutions, offering a wide range of banking services to individuals and businesses.
|
E1178830
|
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: CEC Bank | Statement: [CEC Palace, client, CEC Bank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CEC Bank Context triple: [CEC Palace, client, CEC Bank]
-
A.
Equator Bank
Equator Bank was a financial institution where future Liberian president and economist Ellen Johnson Sirleaf held a professional position during her banking career.
-
B.
United Commercial Bank
United Commercial Bank, now known as UCO Bank, is a major Indian public sector bank headquartered in Kolkata that offers a wide range of banking and financial services.
-
C.
C-Bank
C-Bank is an American freestyle and dance music artist best known for the 1983 club hit "One More Shot."
-
D.
Takasbank
Takasbank is Turkey’s central clearing and settlement institution, providing post-trade, custody, and risk management services for the country’s capital markets.
-
E.
ING Bank
ING Bank is a global Dutch financial institution offering banking, investment, and insurance services to retail and corporate clients.
- 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: CEC Bank Triple: [CEC Palace, client, CEC Bank]
Generated description
CEC Bank is one of Romania’s oldest state-owned financial institutions, offering a wide range of banking services to individuals and businesses.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CEC Bank Target entity description: CEC Bank is one of Romania’s oldest state-owned financial institutions, offering a wide range of banking services to individuals and businesses.
-
A.
Equator Bank
Equator Bank was a financial institution where future Liberian president and economist Ellen Johnson Sirleaf held a professional position during her banking career.
-
B.
United Commercial Bank
United Commercial Bank, now known as UCO Bank, is a major Indian public sector bank headquartered in Kolkata that offers a wide range of banking and financial services.
-
C.
C-Bank
C-Bank is an American freestyle and dance music artist best known for the 1983 club hit "One More Shot."
-
D.
Takasbank
Takasbank is Turkey’s central clearing and settlement institution, providing post-trade, custody, and risk management services for the country’s capital markets.
-
E.
ING Bank
ING Bank is a global Dutch financial institution offering banking, investment, and insurance services to retail and corporate clients.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e61c7508190ba1f675f2092364c |
completed | April 16, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff999da5008190921b3f129787999e |
completed | May 9, 2026, 8:31 p.m. |
| NEDg | Description generation | batch_69ff9a82cadc8190a57f40062d29a998 |
completed | May 9, 2026, 8:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff9b5dbf80819085fdfcdff424511b |
completed | May 9, 2026, 8:38 p.m. |
Created at: April 10, 2026, 4:49 a.m.