Triple
T36950125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louise Ebert |
E914036
|
entity |
| Predicate | role in society |
P15115
|
FINISHED |
| Object | political spouse |
—
|
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: political spouse | Statement: [Louise Ebert, role in society, political spouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: role in society Context triple: [Louise Ebert, role in society, political spouse]
-
A.
socioeconomicRole
Indicates the social and economic position, function, or status an entity holds within a society or system.
-
B.
roleInCommunity
chosen
Indicates the function, position, or set of responsibilities an entity holds within a particular community or group.
-
C.
societyDescription
Indicates a descriptive statement that characterizes or explains the nature, structure, or attributes of a society.
-
D.
ethnicRole
Indicates a role, function, or social position that is specifically associated with or defined by an entity’s ethnicity.
-
E.
society
Indicates a relationship in which individuals or groups are organized into a structured community bound by shared institutions, norms, or social systems.
- 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.