Triple
T7384395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taiping Heavenly Kingdom |
E170343
|
entity |
| Predicate | fallEvent |
P76283
|
FINISHED |
| Object | Qing recapture of Nanjing in 1864 |
—
|
LITERAL 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: Qing recapture of Nanjing in 1864 | Statement: [Taiping Heavenly Kingdom, fallEvent, Qing recapture of Nanjing in 1864]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fallEvent Context triple: [Taiping Heavenly Kingdom, fallEvent, Qing recapture of Nanjing in 1864]
-
A.
fallsOn
Indicates that one entity descends due to gravity and comes to rest upon the surface of another entity.
-
B.
fellOn
Indicates that one entity moved downward, typically due to gravity, and came to rest on the surface of another entity.
-
C.
fallsFrom
Indicates that one entity moves downward or drops starting from the location or position of another entity.
-
D.
fallCause
Indicates that one event or condition causes or brings about another event of falling or decline.
-
E.
fallsIn
Indicates that one entity is located within, contained by, or geographically/administratively included inside another entity.
- F. None of above. chosen
Provenance (4 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. |
| PD | Predicate disambiguation | batch_69c6f0309cc88190b55d278969400294 |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f0be2b1c8190bea06100a7caef2b |
completed | March 27, 2026, 9:03 p.m. |
Created at: March 27, 2026, 3:08 p.m.