Triple
T28774181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress of the Eastern Roman Empire |
E726488
|
entity |
| Predicate | courtSphere |
P168738
|
FINISHED |
| Object | women’s quarters (gynaeceum) |
—
|
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: women’s quarters (gynaeceum) | Statement: [Empress of the Eastern Roman Empire, courtSphere, women’s quarters (gynaeceum)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtSphere Context triple: [Empress of the Eastern Roman Empire, courtSphere, women’s quarters (gynaeceum)]
-
A.
practiceCourt
Indicates that an entity uses or is associated with a particular court for practice or training activities.
-
B.
courtContext
Indicates the legal or judicial setting, circumstances, or framework within which a court-related action or relationship takes place.
-
C.
courtConnection
Indicates a relationship where one entity is linked to another through a legal or judicial proceeding, institution, or decision.
-
D.
courtCategory
Indicates the classification or type of court associated with a legal case, proceeding, or judicial body.
-
E.
courtCategory
Indicates the classification or type of court associated with a legal case or judicial proceeding.
- F. None of above. chosen
Provenance (4 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_69f03199997c8190b6ae43fb19312443 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f67805551c81909e016ae9e3031076 |
completed | May 2, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69f675ff62c48190a634bbb8896973b9 |
completed | May 2, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69f676f73c3481909f01fa69851b7298 |
completed | May 2, 2026, 10:13 p.m. |
Created at: April 28, 2026, 6:17 a.m.