Triple
T24942990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reflecting Pool marks former Fifth Street |
E623510
|
entity |
| Predicate | marksFormerLocationOf |
P59528
|
FINISHED |
| Object | Fifth Street |
—
|
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: Fifth Street | Statement: [Reflecting Pool marks former Fifth Street, marksFormerLocationOf, Fifth Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marksFormerLocationOf Context triple: [Reflecting Pool marks former Fifth Street, marksFormerLocationOf, Fifth Street]
-
A.
marksLocationOf
Indicates that one entity serves as a marker, sign, or indicator specifying the location of another entity.
-
B.
formerlyKnownLocationAs
Indicates that an entity was previously known or referred to by a different location name or designation.
-
C.
locatedAtFormer
chosen
Indicates that an entity is currently located at a place where another entity was previously located.
-
D.
historicalLocationOf
Indicates that a place served as a significant site or setting for an entity during a particular historical period or event.
-
E.
previouslyLocatedIn
Indicates that an entity was located in a particular place or region at some time in the past, but is not necessarily located there now.
- 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_69e2fac6b5a48190a1c38857f00915a9 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f423dbea9881909b32c92c4f1eda9a |
completed | May 1, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69f4210130d08190ae30b7943f7a0bbc |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:31 a.m.