Triple
T16324096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Selma Bouvier |
E396369
|
entity |
| Predicate | maritalHistory |
P94899
|
FINISHED |
| Object | multiple failed marriages |
—
|
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: multiple failed marriages | Statement: [Selma Bouvier, maritalHistory, multiple failed marriages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maritalHistory Context triple: [Selma Bouvier, maritalHistory, multiple failed marriages]
-
A.
characterMaritalHistory
chosen
Indicates a relationship that records the sequence of a character’s past and present marital relationships, including spouses and relevant time periods.
-
B.
maritalPeriodWith
Indicates the time span during which two entities were married to each other.
-
C.
maritalRelations
Indicates a legally or socially recognized spousal relationship or marriage-based connection between two entities.
-
D.
marital status
Indicates the legal or social state of a person’s marriage-related relationship, such as being single, married, divorced, or widowed.
-
E.
hasMarriage
Indicates a marital relationship exists between the two entities, specifying that they are or were legally married to each other.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b8fe988190adee72b23246052f |
completed | April 17, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69e219fc72c881909d452274e7af8238 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.