Triple
T11717916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Utrecht–Zwolle railway |
E278549
|
entity |
| Predicate | signallingSystem |
P19148
|
FINISHED |
| Object | ATB-EG |
E153680
|
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: ATB-EG | Statement: [Utrecht–Zwolle railway, signallingSystem, ATB-EG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ATB-EG Context triple: [Utrecht–Zwolle railway, signallingSystem, ATB-EG]
-
A.
ATB-EG
chosen
ATB-EG is a Dutch train protection and signalling system used to control train speeds and enhance safety on the national railway network.
-
B.
ABT
ABT is the stock ticker symbol for Abbott Laboratories, a global healthcare company specializing in medical devices, diagnostics, nutrition products, and branded generic pharmaceuticals.
-
C.
ABT
ABT is a leading American classical ballet company renowned for its extensive repertoire and international tours.
-
D.
ATN
ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
-
E.
ATN
ATN is the fictional conservative cable news network owned by media mogul Logan Roy in the television series "Succession."
- 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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4c10d988190842acd824135cf15 |
completed | April 10, 2026, 7:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83a9479c81909cbe63d81255a1bf |
completed | April 27, 2026, 3:41 p.m. |
Created at: April 8, 2026, 9:40 p.m.