Triple
T7384679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanjing City Wall |
E170350
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Xuanwu Gate |
E660746
|
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: Xuanwu Gate | Statement: [Nanjing City Wall, hasPart, Xuanwu Gate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xuanwu Gate Context triple: [Nanjing City Wall, hasPart, Xuanwu Gate]
-
A.
Yongdingmen
Yongdingmen is a historic southern gate site of Beijing’s old city wall, now a reconstructed landmark and traffic node at the southern end of the city’s central axis.
-
B.
Fuchengmen
Fuchengmen is a historic gate area in Beijing that once formed part of the old city wall and now serves as a major traffic and commercial hub.
-
C.
Shengji Gate
Shengji Gate is a historic city gate in Qufu, China, associated with the city’s ancient walls and its rich Confucian heritage.
-
D.
Zhonghua Gate
chosen
Zhonghua Gate is a massive, well-preserved Ming dynasty fortress gate in Nanjing, China, renowned for its complex defensive design and historical significance.
-
E.
Xihua Gate
Xihua Gate is a principal entrance to the Zhongnanhai leadership compound in Beijing, closely associated with the central government of the People’s Republic of China.
- 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_69c68a5d0ed08190b6d361e68f813330 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1efe1308190b96eefbff56140be |
completed | March 27, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c810e879e88190a421409194868587 |
completed | March 28, 2026, 5:33 p.m. |
Created at: March 27, 2026, 3:08 p.m.