Triple
T3392149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States v. [Accused] |
E71443
|
entity |
| Predicate | captionPosition |
P21675
|
FINISHED |
| Object | appears at top of charging documents |
—
|
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: appears at top of charging documents | Statement: [United States v. [Accused], captionPosition, appears at top of charging documents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: captionPosition Context triple: [United States v. [Accused], captionPosition, appears at top of charging documents]
-
A.
titlePositionRelation
chosen
Indicates a relationship specifying how a title is positioned or ordered relative to other titles or elements.
-
B.
chartPosition
Indicates the ranking or placement of an item within an ordered chart or list at a specific point in time.
-
C.
stylePositioning
Indicates how an entity is spatially or visually arranged or aligned relative to a reference frame or other elements.
-
D.
positioning
Indicates the spatial or contextual arrangement of one entity relative to another or within a given environment.
-
E.
captainPosition
Indicates that an entity holds the role or position of captain in relation to another entity (such as a team, vessel, or group).
- 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_69ad85a9c4a88190a854019341cb3b60 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb850594c81909b6f8a384fc98cb2 |
completed | March 8, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69adadf705608190975423779430cc58 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:14 p.m.