Triple
T12581612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carrie Lam |
E300351
|
entity |
| Predicate | hasHonorificSuffix |
P341
|
FINISHED |
| Object | GBM |
E990727
|
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: GBM | Statement: [Carrie Lam, hasHonorificSuffix, GBM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GBM Context triple: [Carrie Lam, hasHonorificSuffix, GBM]
-
A.
GBM
chosen
GBM is a prestigious Hong Kong honor, the Grand Bauhinia Medal, awarded for exceptionally distinguished public and community service.
-
B.
GBM
GBM is the Gamma-ray Burst Monitor, an instrument on NASA’s Fermi Gamma-ray Space Telescope designed to detect and study gamma-ray bursts across a wide field of view.
-
C.
HGG
HGG is the stock ticker symbol for Henderson Global Investors, an international asset management firm.
-
D.
GBM Delta
GBM Delta is one of the world’s largest and most fertile river deltas, formed by the confluence of the Ganges, Brahmaputra, and Meghna rivers in South Asia.
-
E.
GBS
GBS is a post-nominal honor awarded by the Hong Kong government, standing for the Gold Bauhinia Star, one of the region’s highest civilian honors.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954b97a508190b6c901c506441dd0 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ebab65081908a174586f0ebb16f |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 9, 2026, 5:02 p.m.