Triple
T10193544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhumel River |
E238099
|
entity |
| Predicate | carved |
P49679
|
FINISHED |
| Object | gorges of Constantine |
—
|
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: gorges of Constantine | Statement: [Rhumel River, carved, gorges of Constantine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carved Context triple: [Rhumel River, carved, gorges of Constantine]
-
A.
carvedInto
Indicates that one entity has been shaped, cut, or sculpted so that it takes the form or likeness of another entity.
-
B.
carvedThrough
chosen
Indicates that one entity has cut or worn a path through another entity, typically by force, motion, or gradual erosion.
-
C.
carvedOutOf
Indicates that one entity has been physically shaped, cut, or formed from the material of another entity.
-
D.
carvedBy
Indicates that one entity has been shaped, cut, or sculpted from a material by another entity through a carving process.
-
E.
hasCarving
Indicates that one entity features or contains a carved design, inscription, or sculpted detail that is associated with or applied to another entity.
- 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_69ca84de1b208190bf17bb305b002605 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdedc675008190b8248325f5a208bf |
completed | April 2, 2026, 4:17 a.m. |
| PD | Predicate disambiguation | batch_69cd7c8477648190bc55c56aeec507d3 |
completed | April 1, 2026, 8:13 p.m. |
Created at: March 30, 2026, 9:13 p.m.