Triple
T17026166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golden Harvest |
E413068
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Leonard Ho |
E1245663
|
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: Leonard Ho | Statement: [Golden Harvest, foundedBy, Leonard Ho]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leonard Ho Context triple: [Golden Harvest, foundedBy, Leonard Ho]
-
A.
Leonard Ho
chosen
Leonard Ho was a prominent Hong Kong film producer and co-founder of Golden Harvest, known for backing major action stars and influential martial arts films.
-
B.
John M. Y. Lee
John M. Y. Lee is an American architect known for designing major civic and institutional buildings, including the Thurgood Marshall Federal Judiciary Building in Washington, D.C.
-
C.
George K. T. Hau
George K. T. Hau is an astronomer known for his work on nearby galaxies, including the discovery of the dwarf spheroidal galaxy Andromeda VI.
-
D.
Leonard Wu
Leonard Wu is an American actor known for his roles in film and television, including a notable appearance in the thriller "While She Was Out."
-
E.
Stanley Tang
Stanley Tang is a technology entrepreneur best known as a co-founder of the food delivery platform DoorDash.
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d46a5081908bc5681621dd8534 |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0139ef70208190b26029511e91afb0 |
completed | May 11, 2026, 2:07 a.m. |
Created at: April 10, 2026, 5:33 a.m.