Triple
T1846741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colchis |
E41299
|
entity |
| Predicate | succeededBy |
P78
|
FINISHED |
| Object |
Egrisi
Egrisi was a medieval Georgian kingdom that emerged as a successor to ancient Colchis in the western Caucasus region.
|
E206092
|
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: Egrisi | Statement: [Colchis, succeededBy, Egrisi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Egrisi Context triple: [Colchis, succeededBy, Egrisi]
-
A.
Comino
Comino is a small, sparsely populated Maltese island in the Mediterranean Sea, best known for its clear waters and the popular Blue Lagoon.
-
B.
Lozanella
Lozanella is a small genus of flowering plants in the hemp family Cannabaceae, native to parts of Central and South America.
-
C.
Bougros
Bougros is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, France, known for producing high-quality Chardonnay wines.
-
D.
Melide
Melide is a Swiss municipality in the canton of Ticino, known for its scenic location on Lake Lugano and the Swissminiatur open-air miniature park.
-
E.
Enodia
Enodia is an epithet of the Greek goddess Hecate that emphasizes her role as a protector and guide along roads, thresholds, and liminal spaces.
- 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: Egrisi Triple: [Colchis, succeededBy, Egrisi]
Generated description
Egrisi was a medieval Georgian kingdom that emerged as a successor to ancient Colchis in the western Caucasus region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Egrisi Target entity description: Egrisi was a medieval Georgian kingdom that emerged as a successor to ancient Colchis in the western Caucasus region.
-
A.
Comino
Comino is a small, sparsely populated Maltese island in the Mediterranean Sea, best known for its clear waters and the popular Blue Lagoon.
-
B.
Lozanella
Lozanella is a small genus of flowering plants in the hemp family Cannabaceae, native to parts of Central and South America.
-
C.
Bougros
Bougros is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, France, known for producing high-quality Chardonnay wines.
-
D.
Melide
Melide is a Swiss municipality in the canton of Ticino, known for its scenic location on Lake Lugano and the Swissminiatur open-air miniature park.
-
E.
Enodia
Enodia is an epithet of the Greek goddess Hecate that emphasizes her role as a protector and guide along roads, thresholds, and liminal spaces.
- 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_69a88648cd44819093303206d96d76ad |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb052e0a8819091bbc0da0e0a20fb |
completed | March 7, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adc9c2e0a081909f521e6f73956239 |
completed | March 8, 2026, 7:10 p.m. |
| NEDg | Description generation | batch_69adcaf1917c819090eac27de62494ca |
completed | March 8, 2026, 7:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adcbba64588190aa0ebd2b6f67afa7 |
completed | March 8, 2026, 7:19 p.m. |
Created at: March 4, 2026, 7:33 p.m.