Triple
T5411360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Jerusalem |
E121018
|
entity |
| Predicate | comesDownFrom |
P57509
|
FINISHED |
| Object | heaven |
—
|
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: heaven | Statement: [New Jerusalem, comesDownFrom, heaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comesDownFrom Context triple: [New Jerusalem, comesDownFrom, heaven]
-
A.
descentFrom
Indicates that one entity is a descendant of another, typically through a lineage or ancestral relationship.
-
B.
downstreamFrom
Indicates that one entity is located or occurs at a point further along the natural flow or direction of another entity, typically in a linear or directional system such as a river, pipeline, or process sequence.
-
C.
fallsDownBefore
Indicates that one event or entity moves downward or collapses prior in time to another specified event or entity.
-
D.
fallsFrom
chosen
Indicates that one entity moves downward or drops starting from the location or position of another entity.
-
E.
cededFrom
Indicates that control, ownership, or sovereignty over something was transferred away from a source entity to another entity, typically through a formal or legal act of cession.
- 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_69bd463a41cc8190b32ff5af2b96ca93 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd87985ee0819092a9a5cd6a948138 |
completed | March 20, 2026, 5:44 p.m. |
| PD | Predicate disambiguation | batch_69bd8467e6b48190b9eaa9de67072e06 |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:05 p.m.