Triple
T12574859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herod’s Northern Palace |
E300179
|
entity |
| Predicate | lowerTerraceUse |
P105498
|
FINISHED |
| Object | garden and leisure area |
—
|
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: garden and leisure area | Statement: [Herod’s Northern Palace, lowerTerraceUse, garden and leisure area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerTerraceUse Context triple: [Herod’s Northern Palace, lowerTerraceUse, garden and leisure area]
-
A.
lowFloor
Indicates that something has a floor positioned close to ground level, allowing easy, step-free access.
-
B.
lowerLocation
Indicates that one entity is located physically below or at a lower vertical position relative to another entity.
-
C.
lowerCourseEnvironment
Indicates that one course is conducted in a less advanced or less demanding learning environment compared to another course.
-
D.
LowerBayUsage
Indicates that the usage or activity level of a lower bay area is reduced compared to a previous state or relative standard.
-
E.
lowerLevelServes
Indicates that a lower-level component, service, or entity provides functionality or support to a higher-level component, service, or entity.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9550d84908190aea0f50055f6d92e |
completed | April 10, 2026, 7:52 p.m. |
| PD | Predicate disambiguation | batch_69d95414692881909c52a1de7d224b44 |
completed | April 10, 2026, 7:48 p.m. |
| PDg | Predicate description generation | batch_69d9550af6d48190a40e349ed0424be3 |
completed | April 10, 2026, 7:52 p.m. |
Created at: April 9, 2026, 4:46 p.m.