Triple
T3249482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J’accuse…! |
E68140
|
entity |
| Predicate | legalConsequenceForAuthor |
P36372
|
FINISHED |
| Object | Émile Zola’s prosecution for libel |
—
|
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: Émile Zola’s prosecution for libel | Statement: [J’accuse…!, legalConsequenceForAuthor, Émile Zola’s prosecution for libel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalConsequenceForAuthor Context triple: [J’accuse…!, legalConsequenceForAuthor, Émile Zola’s prosecution for libel]
-
A.
violationConsequences
chosen
Indicates the negative outcomes, penalties, or repercussions that result from a violation of a rule, law, or agreement.
-
B.
consequenceOfRevocation
Indicates that something occurs as a direct result of a prior revocation event or decision.
-
C.
legalConstraint
Indicates that one entity imposes or is subject to a rule, restriction, or requirement defined by a legal or regulatory framework in relation to another entity or action.
-
D.
hasAuthor
Indicates that an entity is written or created by a specific author.
-
E.
authorshipStatus
Indicates the current state or condition of an entity’s role as an author in relation to a work (e.g., confirmed, disputed, anonymous, or pending).
- 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_69ad858e4c708190aa31d486cfee8a6a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf3fc3c8819080ac95974581ca0e |
completed | March 8, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69ada41837e48190933572165be0ca38 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.