Triple
T19064512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tao-Klarjeti |
E466618
|
entity |
| Predicate | ruledBy |
P3022
|
FINISHED |
| Object |
Princes of Tao
The Princes of Tao were a medieval Georgian noble dynasty that governed the historic region of Tao-Klarjeti and played a key role in the formation of the unified Georgian kingdom.
|
E1357591
|
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: Princes of Tao | Statement: [Tao-Klarjeti, ruledBy, Princes of Tao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Princes of Tao Context triple: [Tao-Klarjeti, ruledBy, Princes of Tao]
-
A.
Prince of Dai
Prince of Dai was the noble title held by Liu Heng before he became Emperor Wen of the Western Han dynasty in ancient China.
-
B.
Prince of Dai
The Prince of Dai was the noble title held by Emperor Gong of Sui before he ascended the throne of the Sui dynasty in China.
-
C.
Prince of Dai
Prince of Dai was a noble title held by Tuoba Gui before he founded the Northern Wei dynasty in early medieval China.
-
D.
Prince of Duan
Prince of Duan was the noble title held by Emperor Huizong of the Song dynasty before he ascended the throne.
-
E.
Prince of Yan
Prince of Yan was the noble title held by Zhu Di before he became the Yongle Emperor of the Ming dynasty.
- 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: Princes of Tao Triple: [Tao-Klarjeti, ruledBy, Princes of Tao]
Generated description
The Princes of Tao were a medieval Georgian noble dynasty that governed the historic region of Tao-Klarjeti and played a key role in the formation of the unified Georgian kingdom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Princes of Tao Target entity description: The Princes of Tao were a medieval Georgian noble dynasty that governed the historic region of Tao-Klarjeti and played a key role in the formation of the unified Georgian kingdom.
-
A.
Prince of Dai
The Prince of Dai was the noble title held by Emperor Gong of Sui before he ascended the throne of the Sui dynasty in China.
-
B.
Prince of Dai
Prince of Dai was the noble title held by Liu Heng before he became Emperor Wen of the Western Han dynasty in ancient China.
-
C.
Prince of Dai
Prince of Dai was a noble title held by Tuoba Gui before he founded the Northern Wei dynasty in early medieval China.
-
D.
Prince of Duan
Prince of Duan was the noble title held by Emperor Huizong of the Song dynasty before he ascended the throne.
-
E.
Prince of Yan
Prince of Yan was the noble title held by Zhu Di before he became the Yongle Emperor of the Ming dynasty.
- 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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e19799d8819099d0b848771ae425 |
completed | April 20, 2026, 8:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05d3569e5881909b6493ce9ac447a5 |
completed | May 14, 2026, 1:51 p.m. |
| NEDg | Description generation | batch_6a05d5c28a708190bf31c547522380db |
completed | May 14, 2026, 2:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05d74b87048190b02383d4c0769c2d |
completed | May 14, 2026, 2:08 p.m. |
Created at: April 10, 2026, 12:03 p.m.