Triple
T30053165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navy legal assistance program |
E763655
|
entity |
| Predicate | accessedAt |
P174405
|
FINISHED |
| Object | Navy legal assistance offices |
—
|
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: Navy legal assistance offices | Statement: [Navy legal assistance program, accessedAt, Navy legal assistance offices]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessedAt Context triple: [Navy legal assistance program, accessedAt, Navy legal assistance offices]
-
A.
accessedAfter
Indicates that one entity is accessed only after another entity has already been accessed in time or sequence.
-
B.
enteredAt
Indicates the time or place at which an entity entered or was recorded as entering a particular context, system, or location.
-
C.
visitedDate
Indicates the specific date on which one entity visited or was present at another entity or location.
-
D.
bestVisitedAt
Indicates the optimal time or conditions under which a place or entity should be visited.
-
E.
observedSince
Indicates that one entity has been continuously or repeatedly observed starting from a specified point in time.
- F. None of above. chosen
Provenance (4 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_69f224716378819087a722e487832b70 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6c20f209081909fb9ac8f95069f04 |
completed | May 3, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2415fc81908c23c311aebce66f |
completed | May 3, 2026, 3:12 a.m. |
| PDg | Predicate description generation | batch_69f6c125695c81909704c67bef4ce5b2 |
completed | May 3, 2026, 3:29 a.m. |
Created at: April 29, 2026, 6:56 p.m.