Triple
T14683394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berosus |
E344843
|
entity |
| Predicate | fragmentsPreservedBy |
P50770
|
FINISHED |
| Object |
Syncellus
Syncellus was a Byzantine chronicler and ecclesiastic best known for compiling the historical work "Ekloge Chronographias," which preserves excerpts from many earlier authors.
|
E1113130
|
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: Syncellus | Statement: [Berosus, fragmentsPreservedBy, Syncellus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Syncellus Context triple: [Berosus, fragmentsPreservedBy, Syncellus]
-
A.
Opsarius
Opsarius is a genus of small freshwater cyprinid fishes native to rivers and streams of South and Southeast Asia.
-
B.
Dascylus
Dascylus is a figure from ancient Lydian mythology or legend, known primarily as the son of King Gyges.
-
C.
Alectura
Alectura is a genus of large, ground-dwelling Australian birds in the megapode family, best known for the brush-turkey.
-
D.
Catholicon
The Catholicon is the large central nave and main Greek Orthodox worship space within Jerusalem’s Church of the Holy Sepulchre.
-
E.
Almodis
Almodis was a medieval noblewoman known for her influential dynastic marriages and role in the politics of 11th-century Catalonia and southern France.
- 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: Syncellus Triple: [Berosus, fragmentsPreservedBy, Syncellus]
Generated description
Syncellus was a Byzantine chronicler and ecclesiastic best known for compiling the historical work "Ekloge Chronographias," which preserves excerpts from many earlier authors.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Syncellus Target entity description: Syncellus was a Byzantine chronicler and ecclesiastic best known for compiling the historical work "Ekloge Chronographias," which preserves excerpts from many earlier authors.
-
A.
Opsarius
Opsarius is a genus of small freshwater cyprinid fishes native to rivers and streams of South and Southeast Asia.
-
B.
Dascylus
Dascylus is a figure from ancient Lydian mythology or legend, known primarily as the son of King Gyges.
-
C.
Alectura
Alectura is a genus of large, ground-dwelling Australian birds in the megapode family, best known for the brush-turkey.
-
D.
Catholicon
The Catholicon is the large central nave and main Greek Orthodox worship space within Jerusalem’s Church of the Holy Sepulchre.
-
E.
Almodis
Almodis was a medieval noblewoman known for her influential dynastic marriages and role in the politics of 11th-century Catalonia and southern France.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb56a51ec8190941684fd562a7182 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde18592088190892ae1cc371165be |
completed | May 8, 2026, 1:13 p.m. |
| NEDg | Description generation | batch_69fde4782f188190aa2071e39d768168 |
completed | May 8, 2026, 1:26 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fde4d080148190a0df7aae8b3afc93 |
completed | May 8, 2026, 1:27 p.m. |
Created at: April 10, 2026, 1:28 a.m.