Triple
T7093042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Davenport |
E165246
|
entity |
| Predicate | legalTeam |
P8814
|
FINISHED |
| Object | Brady’s prosecution team |
—
|
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: Brady’s prosecution team | Statement: [Tom Davenport, legalTeam, Brady’s prosecution team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalTeam Context triple: [Tom Davenport, legalTeam, Brady’s prosecution team]
-
A.
legalRepresentation
chosen
Indicates that one entity formally acts on behalf of another in legal matters, such as providing counsel, advocacy, or defense within a legal system.
-
B.
lawFirm
Indicates a relationship where one entity is a law firm that provides legal services or representation to another entity.
-
C.
legalTool
Indicates a relationship where something functions as a legal instrument, mechanism, or means used to achieve or regulate a legal purpose or outcome.
-
D.
legalMatters
Indicates that one entity is involved with, concerned about, or responsible for legal issues, processes, or obligations related to another entity or context.
-
E.
legalParties
Indicates that the related entities are formally recognized participants in a legal relationship, case, contract, or proceeding.
- 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_69c6887e8c10819091cee237560d32da |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e532513c8190968eea8a0d3235a0 |
completed | March 27, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69c6e1c172148190bf290c07bf579d1f |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:41 p.m.