Triple
T6747632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Soames |
E154257
|
entity |
| Predicate | honorificSuffix |
P341
|
FINISHED |
| Object | LG |
E5305
|
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: LG | Statement: [Mary Soames, honorificSuffix, LG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LG Context triple: [Mary Soames, honorificSuffix, LG]
-
A.
LG
chosen
LG is the post-nominal abbreviation used by members of the prestigious British chivalric Order of the Garter.
-
B.
LG
LG is an abbreviation commonly used to refer to the Local Group, the galaxy group that includes the Milky Way, Andromeda, and numerous smaller galaxies.
-
C.
LG
LG is the vehicle registration code used on license plates for the Province of Liège in Belgium.
-
D.
LG
LG is the standard abbreviation for *Lumen Gentium*, the Second Vatican Council’s Dogmatic Constitution on the Church, which outlines Catholic teaching on the nature and mission of the Church.
-
E.
LG Electronics
LG Electronics is a South Korean multinational electronics company known for producing a wide range of consumer electronics, home appliances, and mobile devices.
- 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_69c6880ef37881909268a5a7299b9293 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1d785dc81909c033084d2068568 |
completed | March 27, 2026, 6:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b180f188190b380909c46fbce40 |
completed | March 27, 2026, 10:56 p.m. |
Created at: March 27, 2026, 2:11 p.m.