Triple
T3236735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Einstein–Rosen bridge |
E67871
|
entity |
| Predicate | timeSymmetry |
P47525
|
FINISHED |
| Object | time-symmetric geometry |
—
|
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: time-symmetric geometry | Statement: [Einstein–Rosen bridge, timeSymmetry, time-symmetric geometry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeSymmetry Context triple: [Einstein–Rosen bridge, timeSymmetry, time-symmetric geometry]
-
A.
timeExistence
Indicates the period or duration during which an entity exists or is valid.
-
B.
testsSymmetry
Indicates that one entity evaluates or verifies whether a relationship or property holds identically in both directions between two entities.
-
C.
time
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
D.
timescale
Indicates the temporal scale or duration over which a process, relationship, or effect occurs or is evaluated.
-
E.
timeDependence
Indicates that one entity’s state, value, or behavior is determined by or varies as a function of another entity over time.
- 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaee05d34819095dbce4db6ac8613 |
completed | March 8, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ada4159e0481908cbbdd750f5e08c7 |
completed | March 8, 2026, 4:30 p.m. |
| PDg | Predicate description generation | batch_69ada698eeb48190a1f5762fdd3b7b63 |
completed | March 8, 2026, 4:40 p.m. |
Created at: March 8, 2026, 3:08 p.m.