Triple
T2478004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States v. Daniel Ellsberg |
E55133
|
entity |
| Predicate | numberOfCountsInitially |
P17874
|
FINISHED |
| Object | dozens of felony counts |
—
|
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: dozens of felony counts | Statement: [United States v. Daniel Ellsberg, numberOfCountsInitially, dozens of felony counts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfCountsInitially Context triple: [United States v. Daniel Ellsberg, numberOfCountsInitially, dozens of felony counts]
-
A.
registerCount
Indicates the number of registers associated with or allocated to a given entity in a system.
-
B.
numberOfInstances
chosen
Indicates the quantity or count of distinct occurrences or instances associated with a given entity or context.
-
C.
numberOfPositions
Indicates the total count of distinct positions or roles associated with a given entity.
-
D.
numberOfCells
Indicates the total count of individual cells associated with or contained in a given entity.
-
E.
movementCount
Indicates the number of times a movement or relocation action has occurred between the related entities.
- 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_69ab49e279e88190ab10d7248aea9d11 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd1eb3be481908fa7c6b8f1c78209 |
completed | March 7, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69abd0b5e3d481909a5cbc4a96edd24f |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:45 p.m.