Triple
T26987796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Continental (New York) |
E679779
|
entity |
| Predicate | penaltyForRuleBreaking |
P112422
|
FINISHED |
| Object | excommunication |
—
|
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: excommunication | Statement: [The Continental (New York), penaltyForRuleBreaking, excommunication]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penaltyForRuleBreaking Context triple: [The Continental (New York), penaltyForRuleBreaking, excommunication]
-
A.
penaltyRules
Indicates the rules or conditions under which penalties are defined, applied, or enforced in a given context.
-
B.
penaltyPoints
Indicates that a certain number of negative points or demerits are assigned to an entity as a consequence of a rule violation, error, or infraction.
-
C.
penaltyMechanism
chosen
Indicates a relationship where a rule, system, or process imposes a negative consequence or sanction in response to certain actions or conditions.
-
D.
defaultPenalty
Indicates that a standard or automatically applied penalty is imposed in the absence of a specific or overridden penalty.
-
E.
reasonForPunishment
Indicates that one entity is the cause, justification, or grounds for another entity receiving a punishment.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6215b9bc881909614a84c9f0dc499 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f61b3ee7b08190a0a1bc5d26b757aa |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 6:49 a.m.