Triple
T27635277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | killing of Philip Barton Key II |
E696452
|
entity |
| Predicate | hasLegalDefenseType |
P1135
|
FINISHED |
| Object | insanity defense |
—
|
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: insanity defense | Statement: [killing of Philip Barton Key II, hasLegalDefenseType, insanity defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLegalDefenseType Context triple: [killing of Philip Barton Key II, hasLegalDefenseType, insanity defense]
-
A.
typeOfDefense
chosen
Indicates the specific kind or category of defense employed or possessed in a given context.
-
B.
hasDefenseCounsel
Indicates that a person or party is represented or assisted by a defense attorney or legal counsel in a legal matter.
-
C.
hasLegalDefinitionIn
Indicates that something possesses an official legal definition within a specified legal source, system, or jurisdiction.
-
D.
containsLawType
Indicates that one entity includes or is associated with a specific type or category of law.
-
E.
hasLegalSystemType
Indicates that an entity possesses or is governed by a particular type or form of legal system.
- 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc53f4f881908dcc698687bbb64d |
completed | May 3, 2026, 7:42 a.m. |
Created at: April 27, 2026, 2:23 p.m.