Triple
T10510336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macrinus |
E247894
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Nonia Celsa
Nonia Celsa was the little-known wife of the Roman emperor Macrinus, associated with the Severan period of the early 3rd century CE.
|
E868084
|
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: Nonia Celsa | Statement: [Macrinus, spouse, Nonia Celsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nonia Celsa Context triple: [Macrinus, spouse, Nonia Celsa]
-
A.
Isaura Palaia
Isaura Palaia was an ancient city of the Isauria region in Asia Minor, known as one of its principal urban centers in classical antiquity.
-
B.
Camile Velasco
Camile Velasco is a Filipino-American singer who gained national recognition as a finalist on the third season of the television talent show American Idol.
-
C.
Amada Cruz
Amada Cruz is an American museum director and arts administrator known for leading major art institutions, including serving as director of the Seattle Art Museum.
-
D.
Cristeta
Cristeta is a Filipina-American chef best known as the longtime White House Executive Chef.
-
E.
Maria Mauban
Maria Mauban was a French actress known for her roles in European cinema of the 1940s and 1950s, including notable performances in Italian neorealist and French films.
- 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: Nonia Celsa Triple: [Macrinus, spouse, Nonia Celsa]
Generated description
Nonia Celsa was the little-known wife of the Roman emperor Macrinus, associated with the Severan period of the early 3rd century CE.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Nonia Celsa Target entity description: Nonia Celsa was the little-known wife of the Roman emperor Macrinus, associated with the Severan period of the early 3rd century CE.
-
A.
Isaura Palaia
Isaura Palaia was an ancient city of the Isauria region in Asia Minor, known as one of its principal urban centers in classical antiquity.
-
B.
Camile Velasco
Camile Velasco is a Filipino-American singer who gained national recognition as a finalist on the third season of the television talent show American Idol.
-
C.
Amada Cruz
Amada Cruz is an American museum director and arts administrator known for leading major art institutions, including serving as director of the Seattle Art Museum.
-
D.
Cristeta
Cristeta is a Filipina-American chef best known as the longtime White House Executive Chef.
-
E.
Maria Mauban
Maria Mauban was a French actress known for her roles in European cinema of the 1940s and 1950s, including notable performances in Italian neorealist and French films.
- 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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509b542088190868531f84deaf9e4 |
completed | April 7, 2026, 1:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dcee1db081908c791867e2438d30 |
completed | April 10, 2026, 11:20 a.m. |
| NEDg | Description generation | batch_69d8e8ca94508190a2a6beca7f01fbd8 |
completed | April 10, 2026, 12:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d9020bce488190b78e555cdd5caec4 |
completed | April 10, 2026, 1:58 p.m. |
Created at: April 6, 2026, 12:27 p.m.