Triple
T6008858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capitolium |
E133780
|
entity |
| Predicate | topographicalRelation |
P17188
|
FINISHED |
| Object | overlooks Roman Forum |
—
|
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: overlooks Roman Forum | Statement: [Capitolium, topographicalRelation, overlooks Roman Forum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topographicalRelation Context triple: [Capitolium, topographicalRelation, overlooks Roman Forum]
-
A.
hasTopographicalRole
Indicates that an entity serves a specific functional or positional role within a topographical or spatial context.
-
B.
spatialRelation
chosen
Indicates a spatial relationship between entities, specifying how one is positioned or located relative to another in space.
-
C.
arealRelation
Indicates a spatial relationship between areas, such as overlap, containment, adjacency, or relative positioning between two regions.
-
D.
geologicalRelation
Indicates a spatial, temporal, or causal relationship between geological features or events, such as how rock units, structures, or formations are positioned, ordered, or interact with one another.
-
E.
datumRelation
Indicates a relationship where one piece of data is connected to, derived from, or otherwise associated with another piece of data.
- 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_69c0087361a48190905c6b55969852b8 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f154ca481909431baf4feecc16d |
completed | March 22, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69c049e4daf4819099bf870dc700e0a2 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:06 p.m.