Triple
T26858348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battleground National Cemetery |
E676256
|
entity |
| Predicate | burialsMostlyFrom |
P45931
|
FINISHED |
| Object | Battle of Fort Stevens |
—
|
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: Battle of Fort Stevens | Statement: [Battleground National Cemetery, burialsMostlyFrom, Battle of Fort Stevens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: burialsMostlyFrom Context triple: [Battleground National Cemetery, burialsMostlyFrom, Battle of Fort Stevens]
-
A.
hasBurialsFrom
chosen
Indicates that a location or site contains burials originating from a specified time period, culture, or source.
-
B.
burials
Indicates that one entity is interred or laid to rest in a grave or burial site associated with another entity.
-
C.
burialsUntil
Indicates the number of burial events that remain or are scheduled to occur up to a specified point in time or condition.
-
D.
hasBurialsOf
Indicates that a location or site contains or includes the burial places of certain individuals or groups.
-
E.
eraOfMostBurials
Indicates the historical time period during which the greatest number of burials occurred for a given site or context.
- 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_69eee9b9d7708190a15d7485709ae981 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61b9a5de88190b91ba255dc74b6fc |
completed | May 2, 2026, 3:43 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:23 a.m.