Triple
T8881577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portalegre |
E211422
|
entity |
| Predicate | vehicleRegistrationCode |
P1173
|
FINISHED |
| Object | PG |
E178614
|
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: PG | Statement: [Portalegre, vehicleRegistrationCode, PG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PG Context triple: [Portalegre, vehicleRegistrationCode, PG]
-
A.
PG
PG is the common abbreviation for Project Gutenberg, a pioneering digital library offering free access to thousands of public-domain ebooks.
-
B.
PG
chosen
PG is the international vehicle registration code used for Podgorica, the capital city of Montenegro.
-
C.
PG
PG is the stock ticker symbol for Procter & Gamble, a major American multinational consumer goods company known for brands across household, personal care, and hygiene products.
-
D.
PG
PG is the commonly used abbreviation for Gdańsk University of Technology, a major technical university in Gdańsk, Poland.
-
E.
GV
GV is the venture capital investment arm of Alphabet Inc., focused on funding and supporting innovative technology startups.
- 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6168e3d881908c58cf11cf5f9a0e |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfabca74888190934593d6504fbed1 |
completed | April 3, 2026, noon |
Created at: March 30, 2026, 6:53 p.m.