Triple
T4063603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | West Cemetery, Amherst, Massachusetts, United States |
E86271
|
entity |
| Predicate | hasGraveMarkerStyle |
P11281
|
FINISHED |
| Object | 19th-century marble headstones |
—
|
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: 19th-century marble headstones | Statement: [West Cemetery, Amherst, Massachusetts, United States, hasGraveMarkerStyle, 19th-century marble headstones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGraveMarkerStyle Context triple: [West Cemetery, Amherst, Massachusetts, United States, hasGraveMarkerStyle, 19th-century marble headstones]
-
A.
hasGravestoneStyle
chosen
Indicates that an entity’s gravestone is characterized by or associated with a particular style or design.
-
B.
hasGravestone
Indicates that one entity possesses, is associated with, or is commemorated by a gravestone.
-
C.
hasTypeOfGrave
Indicates that an entity is associated with a specific kind or category of grave.
-
D.
hasFindAGraveID
Indicates that an entity is associated with a specific identifier used in the Find a Grave online memorial database.
-
E.
hasGraveGoods
Indicates that a burial or grave contains associated objects or goods placed with the deceased.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.