Triple
T15459443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu |
E371857
|
entity |
| Predicate | notableBearer |
P458
|
FINISHED |
| Object | Liu Xiang |
E719110
|
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: Liu Xiang | Statement: [Liu, notableBearer, Liu Xiang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liu Xiang Context triple: [Liu, notableBearer, Liu Xiang]
-
A.
Liu Xiang
chosen
Liu Xiang was a Chinese educator and politician active in the early 20th century who played a key role in developing higher education in China.
-
B.
Wang Junxia
Wang Junxia is a Chinese long-distance runner who set multiple world records in the 1990s and won Olympic gold in the 10,000 meters.
-
C.
Wu Dajing
Wu Dajing is a Chinese short track speed skater and Olympic champion known for his world-record performances in the 500-meter event.
-
D.
Edwin Moses
Edwin Moses is an American track and field legend best known for his dominance in the 400-meter hurdles, including an unprecedented winning streak and multiple Olympic gold medals.
-
E.
Liu Li
Liu Li was a son of Liu Bei, the founding emperor of Shu Han during China’s Three Kingdoms period.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f1623f0819086f6fc2bfd536609 |
completed | April 16, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff21b9817c819082e5c571b08bafb5 |
completed | May 9, 2026, 11:59 a.m. |
Created at: April 10, 2026, 3:32 a.m.