Triple
T22884804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Crossing |
E567573
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Steeltown |
—
|
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: Steeltown | Statement: [The Crossing, followedBy, Steeltown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steeltown Context triple: [The Crossing, followedBy, Steeltown]
-
A.
Steeltown
chosen
Steeltown is a nickname for the Canadian city of Hamilton, reflecting its historic prominence as a major steel-producing industrial center.
-
B.
Steel City
Steel City is a common nickname for Hamilton, Ontario, reflecting its historic role as a major Canadian center of steel production and heavy industry.
-
C.
Steel City
Steel City is a nickname for Lorain, Ohio, reflecting its historic role as a major center of steel production and heavy industry.
-
D.
Steel City
Steel City is the industrial nickname for Pueblo, Colorado, reflecting its historic role as a major steel-producing center in the United States.
-
E.
Steel City
Steel City is a nickname for the industrial city of Salem, reflecting its historical association with steel production and metalworking.
- 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_69e2458a92ec81908fc1cd5f6407d2ab |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17fbfc5848190aa612ea51df5a9ec |
completed | April 29, 2026, 3:49 a.m. |
Created at: April 17, 2026, 3:40 p.m.