Triple
T32630836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John F. Kennedy Memorial at Runnymede |
E834201
|
entity |
| Predicate | inscriptionFrom |
P50857
|
FINISHED |
| Object | John F. Kennedy inaugural address |
—
|
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: John F. Kennedy inaugural address | Statement: [John F. Kennedy Memorial at Runnymede, inscriptionFrom, John F. Kennedy inaugural address]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionFrom Context triple: [John F. Kennedy Memorial at Runnymede, inscriptionFrom, John F. Kennedy inaugural address]
-
A.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
-
B.
inscription
Indicates that text has been written, carved, or engraved onto a surface or object.
-
C.
inscriptionForm
Indicates the physical or structural form in which an inscription is presented (e.g., carved, painted, stamped, or otherwise rendered).
-
D.
inscriptionSupport
Indicates that one entity serves as the physical surface or material on which another entity (an inscription) is written, carved, or otherwise recorded.
-
E.
inscriptionBody
chosen
Indicates that the predicate links an inscription to the textual content or wording that is inscribed.
- 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_69f3492dc2308190a88c6e30a3f3f576 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:07 a.m.