Triple
T8874780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sterling Street |
E211245
|
entity |
| Predicate | systemStyle |
P13268
|
FINISHED |
| Object | IRT |
E63229
|
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: IRT | Statement: [Sterling Street, systemStyle, IRT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IRT Context triple: [Sterling Street, systemStyle, IRT]
-
A.
IRT
chosen
IRT is a major division of the New York City Subway system that operates the numbered (1–7) train lines, originally built by the Interborough Rapid Transit Company.
-
B.
IR
IR is the IATA airline designator assigned to Iran Air, the national flag carrier of Iran.
-
C.
IR
IR is the branding abbreviation used for InterRegio, a category of medium- to long-distance passenger trains operating in several European countries.
-
D.
IRE
IRE is the three-letter World Rugby code representing the Ireland national rugby union team.
-
E.
IER
IER is a division of the U.S. Department of Justice that enforces federal laws protecting immigrants and other workers from employment discrimination based on citizenship or immigration status and national origin.
- 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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc614451d081908804430a72d00edf |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0f9714c8190909587eecbb10e1a |
completed | April 3, 2026, 11:14 a.m. |
Created at: March 30, 2026, 6:52 p.m.