Triple
T20221077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LIRR DM30AC |
E495256
|
entity |
| Predicate | builder |
P3143
|
FINISHED |
| Object | EMD |
—
|
NE NERFINISHED |
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: EMD | Statement: [LIRR DM30AC, builder, EMD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EMD Context triple: [LIRR DM30AC, builder, EMD]
-
A.
EMD
EMD is the commonly used abbreviation for the Engineering Management Division, a professional group focused on the practice and advancement of engineering management.
-
B.
EMD
EMD is the National Rail station code for East Midlands Parkway railway station in England.
-
C.
EMD
EMD is the vehicle registration code assigned to the German town of Emden.
-
D.
EMD
chosen
EMD is a major American manufacturer of diesel-electric locomotives and related railway equipment, historically known for its influential role in the development of modern rail transportation.
-
E.
EMD
EMD is an industry-standard electronic document used in air travel to record and manage ancillary services and fees such as baggage, seat selection, and other optional charges.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd610f881908fdd22b1f8bd2efc |
completed | April 20, 2026, 6:26 p.m. |
Created at: April 11, 2026, 11:39 p.m.