Triple
T8295191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liao dynasty |
E194197
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Xijing (Liao) |
E137853
|
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: Xijing (Liao) | Statement: [Liao dynasty, capital, Xijing (Liao)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xijing (Liao) Context triple: [Liao dynasty, capital, Xijing (Liao)]
-
A.
Xijing
chosen
Xijing is the historical name of Xi'an, one of China’s oldest and most important ancient capitals.
-
B.
Changling
Changling is the largest and best-preserved mausoleum within Beijing’s Ming Tombs complex, built for the Yongle Emperor and his empress.
-
C.
Xinjing
Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
-
D.
Yutian
Yutian is the ancient name of the oasis kingdom and region historically known as Hotan on the southern Silk Road in what is now Xinjiang, China.
-
E.
Longqing
Longqing was the era name of a brief but notable period of the Ming dynasty in China, associated with the reign of the Longqing Emperor in the 16th century.
- 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_69ca82e50ebc81909aa7b260c76bd757 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7df73d4c81909ad9cf0786eb5a20 |
completed | March 31, 2026, 7:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd68a3258481908fe04fed1d00c9ba |
completed | April 1, 2026, 6:49 p.m. |
Created at: March 30, 2026, 5:52 p.m.