Triple
T20244392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leo II of Armenia |
E498383
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Keran of Lampron
Keran of Lampron was a queen consort of the Armenian Kingdom of Cilicia and a member of the influential Lampron noble family.
|
E1419147
|
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: Keran of Lampron | Statement: [Leo II of Armenia, spouse, Keran of Lampron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keran of Lampron Context triple: [Leo II of Armenia, spouse, Keran of Lampron]
-
A.
Kingskettle
Kingskettle is a small village in Fife, Scotland, known historically for its rural character and former linen-weaving industry.
-
B.
Rillieux
Rillieux was a former French commune near Lyon that later became part of the modern municipality of Rillieux-la-Pape.
-
C.
Alkalawa
Alkalawa was the historic capital city of the Hausa kingdom of Gobir in what is now northern Nigeria.
-
D.
Teigne
Teigne is the traditional title held by the monarch of the Serer kingdom of Baol in what is now Senegal.
-
E.
Beloeil
Beloeil is a suburban city in southwestern Quebec, Canada, located along the Richelieu River opposite Mont-Saint-Hilaire and forming part of the greater Montreal area.
- 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: Keran of Lampron Triple: [Leo II of Armenia, spouse, Keran of Lampron]
Generated description
Keran of Lampron was a queen consort of the Armenian Kingdom of Cilicia and a member of the influential Lampron noble family.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Keran of Lampron Target entity description: Keran of Lampron was a queen consort of the Armenian Kingdom of Cilicia and a member of the influential Lampron noble family.
-
A.
Kingskettle
Kingskettle is a small village in Fife, Scotland, known historically for its rural character and former linen-weaving industry.
-
B.
Rillieux
Rillieux was a former French commune near Lyon that later became part of the modern municipality of Rillieux-la-Pape.
-
C.
Alkalawa
Alkalawa was the historic capital city of the Hausa kingdom of Gobir in what is now northern Nigeria.
-
D.
Teigne
Teigne is the traditional title held by the monarch of the Serer kingdom of Baol in what is now Senegal.
-
E.
Beloeil
Beloeil is a suburban city in southwestern Quebec, Canada, located along the Richelieu River opposite Mont-Saint-Hilaire and forming part of the greater Montreal area.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e673a10ab48190a408a5d2c2b0808b |
completed | April 20, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a084b9607b48190bc9c68c4e9b8f9b8 |
completed | May 16, 2026, 10:48 a.m. |
| NEDg | Description generation | batch_6a084be2bcc88190b7d369c07da59c11 |
completed | May 16, 2026, 10:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a084c99487c81908dd132f118846f0c |
completed | May 16, 2026, 10:53 a.m. |
Created at: April 11, 2026, 11:40 p.m.