Triple
T2058359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MIT Building 20 |
E45728
|
entity |
| Predicate | approximateAddress |
P22067
|
FINISHED |
| Object | Vassar Street, MIT campus, Cambridge, MA |
—
|
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: Vassar Street, MIT campus, Cambridge, MA | Statement: [MIT Building 20, approximateAddress, Vassar Street, MIT campus, Cambridge, MA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateAddress Context triple: [MIT Building 20, approximateAddress, Vassar Street, MIT campus, Cambridge, MA]
-
A.
address
Indicates that one entity directs spoken or written communication specifically to another entity.
-
B.
hasApproximateLocation
chosen
Indicates that an entity is associated with a location that is known only imprecisely or within a general area rather than an exact position.
-
C.
streetAddress
Indicates the specific location of an entity in terms of its numbered building and street name within a postal address.
-
D.
addressMode
Indicates how data or resources are accessed or referenced within a system, such as the method or scheme used to locate them.
-
E.
addressType
Indicates the specific kind or category of address associated with an entity (e.g., home, work, billing, or shipping).
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9ae0130819089f7d62005466a45 |
completed | March 7, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_69abb7ad5a7c8190b92575d6053b3fb7 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:40 p.m.