Triple
T10840318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decebalus |
E255867
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object |
Duras
Duras was a Dacian king who ruled before Decebalus and helped lay the groundwork for Dacia’s later resistance against Rome.
|
E889320
|
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: Duras | Statement: [Decebalus, predecessor, Duras]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duras Context triple: [Decebalus, predecessor, Duras]
-
A.
Duras
Duras is a traditional red wine grape variety from southwest France, known for producing deeply colored, spicy wines with moderate tannins.
-
B.
de Duras
De Duras is a French noble family name associated with Louis de Duras, 2nd Earl of Feversham, a Huguenot soldier who became an English peer and military commander under King Charles II.
-
C.
Marguerite Duras
Marguerite Duras was a French novelist, playwright, and filmmaker renowned for her experimental narrative style and works such as "L'Amant" ("The Lover").
-
D.
Patricia Michon
Patricia Michon is an actress known for her role in the 1960 racial drama film "I Passed for White."
-
E.
Melvil Poupaud
Melvil Poupaud is a French actor and filmmaker known for his work in European art-house cinema, including collaborations with directors like Raúl Ruiz and François Ozon.
- 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: Duras Triple: [Decebalus, predecessor, Duras]
Generated description
Duras was a Dacian king who ruled before Decebalus and helped lay the groundwork for Dacia’s later resistance against Rome.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Duras Target entity description: Duras was a Dacian king who ruled before Decebalus and helped lay the groundwork for Dacia’s later resistance against Rome.
-
A.
Duras
Duras is a traditional red wine grape variety from southwest France, known for producing deeply colored, spicy wines with moderate tannins.
-
B.
de Duras
De Duras is a French noble family name associated with Louis de Duras, 2nd Earl of Feversham, a Huguenot soldier who became an English peer and military commander under King Charles II.
-
C.
Marguerite Duras
Marguerite Duras was a French novelist, playwright, and filmmaker renowned for her experimental narrative style and works such as "L'Amant" ("The Lover").
-
D.
Patricia Michon
Patricia Michon is an actress known for her role in the 1960 racial drama film "I Passed for White."
-
E.
Melvil Poupaud
Melvil Poupaud is a French actor and filmmaker known for his work in European art-house cinema, including collaborations with directors like Raúl Ruiz and François Ozon.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7470204548190ba0c724dd9367712 |
completed | April 9, 2026, 6:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb146f04881909f5636e7d0c20b77 |
completed | April 14, 2026, 9:27 p.m. |
| NEDg | Description generation | batch_69dec2534728819095b3693120772da9 |
completed | April 14, 2026, 10:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69dec79b1b548190a74312284f98551c |
completed | April 14, 2026, 11:02 p.m. |
Created at: April 8, 2026, 9:19 p.m.