Triple
T16430471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GEOS-FP |
E399058
|
entity |
| Predicate | timeLatency |
P45126
|
FINISHED |
| Object | near-real-time latency of a few hours |
—
|
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: near-real-time latency of a few hours | Statement: [GEOS-FP, timeLatency, near-real-time latency of a few hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeLatency Context triple: [GEOS-FP, timeLatency, near-real-time latency of a few hours]
-
A.
communicationLatency
chosen
Indicates the time delay between when a communication is sent by one entity and when it is received or processed by another.
-
B.
timeBehind
Indicates that one entity occurs or is positioned later in time than another, lagging behind it on a temporal scale.
-
C.
timeToTravelEndToEnd
Indicates the duration required to traverse from the starting point to the ending point of something (e.g., a route, path, or system) without interruption.
-
D.
timeLimited
Indicates that the relationship or action is constrained to occur or remain valid only within a specific, limited time period.
-
E.
timeSensitivity
Indicates how strongly the relationship or action depends on, changes with, or is constrained by time.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e328fe0f488190ac34aa677c980a20 |
completed | April 18, 2026, 6:47 a.m. |
| PD | Predicate disambiguation | batch_69e22701d2288190bf8676050758f172 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:10 a.m.