Triple
T18947921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianshui |
E463563
|
entity |
| Predicate | associatedWithHistoricalRegion |
P13711
|
FINISHED |
| Object |
Longxi
Longxi is a historic region in what is now Gansu Province, China, long known as a strategic frontier area and administrative commandery in imperial times.
|
E1351861
|
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: Longxi | Statement: [Tianshui, associatedWithHistoricalRegion, Longxi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Longxi Context triple: [Tianshui, associatedWithHistoricalRegion, Longxi]
-
A.
Raoping
Raoping is a coastal county in eastern Guangdong, China, known for its Teochew culture and strategic location along major transport routes.
-
B.
Hexi District
Hexi District is a central urban district of Tianjin, China, known for its commercial areas, educational institutions, and cultural sites along the Hai River.
-
C.
Guanghe
Guanghe was an era name used during the reign of Emperor Ling of the Eastern Han dynasty in ancient China.
-
D.
Tianshui
Tianshui is a historic city in eastern Gansu Province, China, known as an important stop on the ancient Silk Road and for its nearby Maijishan Grottoes.
-
E.
Yongxi
Yongxi was an era name used during the reign of Emperor Taizong of the Song dynasty in imperial China.
- 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: Longxi Triple: [Tianshui, associatedWithHistoricalRegion, Longxi]
Generated description
Longxi is a historic region in what is now Gansu Province, China, long known as a strategic frontier area and administrative commandery in imperial times.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Longxi Target entity description: Longxi is a historic region in what is now Gansu Province, China, long known as a strategic frontier area and administrative commandery in imperial times.
-
A.
Raoping
Raoping is a coastal county in eastern Guangdong, China, known for its Teochew culture and strategic location along major transport routes.
-
B.
Hexi District
Hexi District is a central urban district of Tianjin, China, known for its commercial areas, educational institutions, and cultural sites along the Hai River.
-
C.
Guanghe
Guanghe was an era name used during the reign of Emperor Ling of the Eastern Han dynasty in ancient China.
-
D.
Tianshui
Tianshui is a historic city in eastern Gansu Province, China, known as an important stop on the ancient Silk Road and for its nearby Maijishan Grottoes.
-
E.
Yongxi
Yongxi was an era name used during the reign of Emperor Taizong of the Song dynasty in imperial China.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d540e57c8190bb17fff6d4254320 |
completed | April 20, 2026, 7:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05ad30882081908d08579c728de0f6 |
completed | May 14, 2026, 11:08 a.m. |
| NEDg | Description generation | batch_6a05ae57ce7881909d15b7ac451b98a9 |
completed | May 14, 2026, 11:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05af24cb288190913827bf30a9a010 |
completed | May 14, 2026, 11:16 a.m. |
Created at: April 10, 2026, 11:59 a.m.