Triple
T23511890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lo Xiaohu |
E572447
|
entity |
| Predicate | romanticPartner |
P9994
|
FINISHED |
| Object | Jen Yu |
—
|
NE NERFINISHED |
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: Jen Yu | Statement: [Lo Xiaohu, romanticPartner, Jen Yu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jen Yu Context triple: [Lo Xiaohu, romanticPartner, Jen Yu]
-
A.
Jen Yu
chosen
Jen Yu is a rebellious and highly skilled young noblewoman-turned-warrior from the film "Crouching Tiger, Hidden Dragon," whose secret mastery of martial arts drives much of the story’s conflict.
-
B.
Jean Liu
Jean Liu is a prominent Chinese business executive and technology entrepreneur best known for her leadership role in ride-hailing giant Didi Chuxing.
-
C.
Candice Yu
Candice Yu is a Hong Kong actress known for her work in 1970s and 1980s Cantonese cinema and television.
-
D.
Jenny Chang
Jenny Chang is a Taiwanese entrepreneur best known as one of the co-founders of the global cybersecurity company Trend Micro.
-
E.
Jennifer Lien
Jennifer Lien is an American actress best known for her role as Kes on the television series "Star Trek: Voyager."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa7f583881909e78e8fe2e6e25fe |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:07 p.m.