Triple
T17069920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wu Assassins |
E414188
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Li Jun Li |
E1078171
|
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: Li Jun Li | Statement: [Wu Assassins, starring, Li Jun Li]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Li Jun Li Context triple: [Wu Assassins, starring, Li Jun Li]
-
A.
Li Jun Li
chosen
Li Jun Li is a Chinese-American actress known for her roles in film and television, including a prominent part in Damien Chazelle's 2022 Hollywood epic "Babylon."
-
B.
Xing Li
Xing Li is the creator and original developer of FanFiction.net, one of the largest and earliest online archives for user-written fan fiction.
-
C.
Xing Li
Xing Li is a computer networking expert known for co-authoring IETF standards, including RFC 6145 on IPv4/IPv6 translation mechanisms.
-
D.
Jian Sun
Jian Sun is a Chinese computer vision researcher known for his influential work in deep learning and as a co-author of the seminal ResNet architecture.
-
E.
Yiliang Peng
Yiliang Peng, better known as Doublelift, is a retired professional League of Legends AD carry from North America renowned for his multiple LCS titles and status as one of the region’s greatest players.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbbfb1f08190807301ff6e573cf5 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01235278d48190bacc7881b9eb1ea1 |
completed | May 11, 2026, 12:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.