Triple
T4090321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jackie Chan |
E87688
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | Victoria Peak |
E303784
|
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: Victoria Peak | Statement: [Jackie Chan, placeOfBirth, Victoria Peak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Victoria Peak Context triple: [Jackie Chan, placeOfBirth, Victoria Peak]
-
A.
Victoria Peak
chosen
Victoria Peak is a famous mountain and scenic lookout in Hong Kong known for its panoramic views of the city skyline and Victoria Harbour.
-
B.
Lion Rock
"Lion Rock" is a song by the British electronic music group Culture, recognized as one of their notable works.
-
C.
Chek Lap Kok
Chek Lap Kok is a reclaimed island in Hong Kong best known as the site of Hong Kong International Airport.
-
D.
Table Mountain
Table Mountain is a prominent flat-topped peak in California’s Sierra Nevada, known for its expansive alpine views and rugged granite terrain.
-
E.
Table Mountain
Table Mountain is a flat-topped mountain overlooking Cape Town in South Africa, famous for its distinctive plateau, rich biodiversity, and status as a major natural landmark and tourist attraction.
- 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_69aed94425148190be337845d56fac22 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcab0a1c8190a1b0ca48ebc95b31 |
completed | March 9, 2026, 5 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b69a7908190a53839f7ebfd011c |
completed | March 14, 2026, 2:06 p.m. |
Created at: March 9, 2026, 3:39 p.m.