Triple
T8551476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rubenid dynasty |
E202453
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Vahka |
E202452
|
NE FINISHED |
How this triple was built (2 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: Vahka | Statement: [Rubenid dynasty, capital, Vahka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vahka Context triple: [Rubenid dynasty, capital, Vahka]
-
A.
Vahka
chosen
Vahka was a medieval town that served as an early capital of the Armenian Kingdom of Cilicia.
-
B.
Vauhallan
Vauhallan is a small commune in the southern suburbs of Paris, located in the Essonne department in the Île-de-France region of northern France.
-
C.
Vitasta
Vitasta is the ancient Sanskrit name for the Jhelum River, a historically significant river of the Kashmir region frequently mentioned in Vedic and classical Indian texts.
-
D.
Varkaus
Varkaus is a small industrial town and municipality in the Northern Savonia region of eastern Finland, known for its paper and wood-processing industries.
-
E.
Vaini
Vaini is a coastal village and district on the southern side of Tongatapu in Tonga, known as one of the island’s main population centers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe886fb788190a73e7c76c4f86409 |
completed | March 31, 2026, 3:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6dc7f6fc8190addd5d2bbe1f4408 |
completed | April 2, 2026, 1:23 p.m. |
Created at: March 30, 2026, 6:19 p.m.