Triple
T17814834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dulce of Aragon |
E444809
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Dulce
Dulce was a medieval Aragonese infanta who became Queen consort of Portugal through her marriage to King Sancho I.
|
E1290112
|
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: Dulce | Statement: [Dulce of Aragon, givenName, Dulce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dulce Context triple: [Dulce of Aragon, givenName, Dulce]
-
A.
Dulce
Dulce was a U.S. nuclear test conducted as part of Operation Bowline, a series of underground detonations carried out at the Nevada Test Site during the late 1960s.
-
B.
Dulcé
Dulcé is a stand-up comedian and actress best known as a correspondent on "The Daily Show."
-
C.
Dulcedo
Dulcedo is a Latin term meaning "sweetness" or "delight," often used in Christian liturgical and devotional texts to express spiritual consolation and joy.
-
D.
Dulcy
Dulcy is a 1921 Broadway stage comedy, co-written by Marc Connelly and George S. Kaufman, that helped establish their reputations as leading American playwrights.
-
E.
Dulce Nombre
Dulce Nombre is a town and municipality located in the Copán Department of western Honduras.
- 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: Dulce Triple: [Dulce of Aragon, givenName, Dulce]
Generated description
Dulce was a medieval Aragonese infanta who became Queen consort of Portugal through her marriage to King Sancho I.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dulce Target entity description: Dulce was a medieval Aragonese infanta who became Queen consort of Portugal through her marriage to King Sancho I.
-
A.
Dulce
Dulce was a U.S. nuclear test conducted as part of Operation Bowline, a series of underground detonations carried out at the Nevada Test Site during the late 1960s.
-
B.
Dulcé
Dulcé is a stand-up comedian and actress best known as a correspondent on "The Daily Show."
-
C.
Dulcedo
Dulcedo is a Latin term meaning "sweetness" or "delight," often used in Christian liturgical and devotional texts to express spiritual consolation and joy.
-
D.
Dulcy
Dulcy is a 1921 Broadway stage comedy, co-written by Marc Connelly and George S. Kaufman, that helped establish their reputations as leading American playwrights.
-
E.
Dulce Nombre
Dulce Nombre is a town and municipality located in the Copán Department of western Honduras.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4887e80688190a2ac3308b0e815c6 |
completed | April 19, 2026, 7:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02ff643ca08190a427b7cabfd91dab |
completed | May 12, 2026, 10:22 a.m. |
| NEDg | Description generation | batch_6a0303b3b4c881908960293a5985d8c7 |
completed | May 12, 2026, 10:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a030408cebc8190835c005a5f380793 |
completed | May 12, 2026, 10:42 a.m. |
Created at: April 10, 2026, 10:14 a.m.