Triple
T11273008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cologne Government Region |
E266859
|
entity |
| Predicate | hasVehicleRegistrationCode |
P1173
|
FINISHED |
| Object | GL |
E222968
|
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: GL | Statement: [Cologne Government Region, hasVehicleRegistrationCode, GL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GL Context triple: [Cologne Government Region, hasVehicleRegistrationCode, GL]
-
A.
GL
GL is the commonly used abbreviation for GroenLinks, a Dutch green-left political party focused on environmentalism, social justice, and progressive policies.
-
B.
GL
chosen
GL is the postcode area in the United Kingdom that covers Cheltenham and surrounding parts of Gloucestershire.
-
C.
GL
GL is the stock ticker symbol for Globe Life Inc., a U.S.-based life and health insurance company traded on the New York Stock Exchange.
-
D.
GU
GU is an alternative name or abbreviation for the Gated Recurrent Unit, a type of recurrent neural network architecture used in deep learning for sequence modeling tasks.
-
E.
GU
GU is the two-letter ISO 3166 country code assigned to Guam, an unincorporated territory of the United States in the western Pacific Ocean.
- 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_69d6aac8c2f48190ad0596f1f89f0470 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e965c9048190804ebb48f0a4817b |
completed | April 9, 2026, 6:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4f43633948190b86f5603ac50ec47 |
completed | April 19, 2026, 3:26 p.m. |
Created at: April 8, 2026, 9:31 p.m.