Triple
T9535697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filene's |
E230008
|
entity |
| Predicate | flagshipStoreAddress |
P43977
|
FINISHED |
| Object | 1 Franklin Street, Boston |
—
|
LITERAL 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: 1 Franklin Street, Boston | Statement: [Filene's, flagshipStoreAddress, 1 Franklin Street, Boston]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flagshipStoreAddress Context triple: [Filene's, flagshipStoreAddress, 1 Franklin Street, Boston]
-
A.
flagshipStoreLocation
chosen
Indicates the location where an organization’s primary or most prominent store is situated.
-
B.
flagshipStationLocation
Indicates the location where an organization’s primary or flagship station is situated.
-
C.
flagshipStationFor
Indicates that one station serves as the primary or leading representative station for a particular network, organization, or service.
-
D.
previousFlagshipLocation
Indicates the location where an entity’s flagship (e.g., main store, primary office, or leading site) was situated before it moved to its current flagship location.
-
E.
originalFlagshipName
Indicates the original name by which a flagship entity (such as a primary product, vessel, or brand) was first designated or known.
- F. None of above.
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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98cd6a5c8190835c0910ec38ede3 |
completed | April 1, 2026, 10:14 p.m. |
| PD | Predicate disambiguation | batch_69cca56c44f88190a54a5d2a133bb07e |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 8 p.m.