Triple
T9889816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qin law code |
E181423
|
entity |
| Predicate | notableFindspot |
P31851
|
FINISHED |
| Object |
Liye
Liye is an archaeological site in Hunan, China, renowned for yielding a large cache of Qin dynasty bamboo slips that significantly expanded knowledge of early Chinese legal and administrative systems.
|
E827538
|
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: Liye | Statement: [Qin law code, notableFindspot, Liye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liye Context triple: [Qin law code, notableFindspot, Liye]
-
A.
Jinyang
Jinyang is the historical name of the city now known as Taiyuan, a major urban and industrial center in northern China’s Shanxi province.
-
B.
Xin’an
Xin’an is the former name of Nantou, a historic town in Shenzhen, China, that once served as an important administrative and commercial center in the region.
-
C.
Yangsan
Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
-
D.
Zao Town
Zao Town is a rural Japanese town known for its hot springs, ski resorts, and scenic volcanic landscapes in northeastern Honshu.
-
E.
Kōka
Kōka is a city in Shiga Prefecture, Japan, historically famous as the home of the Kōga ninja tradition.
- 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: Liye Triple: [Qin law code, notableFindspot, Liye]
Generated description
Liye is an archaeological site in Hunan, China, renowned for yielding a large cache of Qin dynasty bamboo slips that significantly expanded knowledge of early Chinese legal and administrative systems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Liye Target entity description: Liye is an archaeological site in Hunan, China, renowned for yielding a large cache of Qin dynasty bamboo slips that significantly expanded knowledge of early Chinese legal and administrative systems.
-
A.
Jinyang
Jinyang is the historical name of the city now known as Taiyuan, a major urban and industrial center in northern China’s Shanxi province.
-
B.
Xin’an
Xin’an is the former name of Nantou, a historic town in Shenzhen, China, that once served as an important administrative and commercial center in the region.
-
C.
Yangsan
Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
-
D.
Zao Town
Zao Town is a rural Japanese town known for its hot springs, ski resorts, and scenic volcanic landscapes in northeastern Honshu.
-
E.
Kōka
Kōka is a city in Shiga Prefecture, Japan, historically famous as the home of the Kōga ninja tradition.
- 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_69ca8283a6708190801af7a25a7ebb9f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb47dfa908190884e96e5e5d6f41f |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1eb08075c81908e017df8048daba8 |
completed | April 5, 2026, 4:54 a.m. |
| NEDg | Description generation | batch_69d1eca8703c8190a473fdafa2a2d273 |
completed | April 5, 2026, 5:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1ed2a1318819087a5b787724fa10c |
completed | April 5, 2026, 5:03 a.m. |
Created at: March 30, 2026, 8:39 p.m.