Triple
T647479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. John’s Cemetery, Worcester, Massachusetts |
E11271
|
entity |
| Predicate | hasGravesOf |
P3803
|
FINISHED |
| Object | local figures from Worcester |
—
|
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: local figures from Worcester | Statement: [St. John’s Cemetery, Worcester, Massachusetts, hasGravesOf, local figures from Worcester]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGravesOf Context triple: [St. John’s Cemetery, Worcester, Massachusetts, hasGravesOf, local figures from Worcester]
-
A.
hasNotableBurials
chosen
Indicates that a place, typically a cemetery or burial site, contains the graves or remains of individuals considered notable or significant.
-
B.
hasCemetery
Indicates that one entity possesses, contains, or includes a cemetery associated with it.
-
C.
hasMausoleum
Indicates that one entity possesses, contains, or is associated with a mausoleum dedicated to another entity.
-
D.
numberOfBurials
Indicates the total count of burial events associated with a given entity.
-
E.
hasTypeOfBurial
Indicates the specific kind or method of burial associated with an entity.
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f1cb24481909d3b41a56b29dee9 |
completed | March 1, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69a49d0c0dcc8190849211d45489a5a7 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.