Triple
T9369391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Operation Thunderbolt |
E225489
|
entity |
| Predicate | timeOnGround_minutes |
P53865
|
FINISHED |
| Object | ~53 |
—
|
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: ~53 | Statement: [Operation Thunderbolt, timeOnGround_minutes, ~53]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOnGround_minutes Context triple: [Operation Thunderbolt, timeOnGround_minutes, ~53]
-
A.
timeAfterTakeoff
Indicates that a specified time point occurs after the moment of takeoff in a flight or launch sequence.
-
B.
actualMissionDurationOnSurface
chosen
Indicates the length of time that a mission actually spent on the surface, as opposed to planned or total mission duration.
-
C.
usesGroundSystem
Indicates that one entity operates, relies on, or interacts with a particular ground-based system to perform its functions or services.
-
D.
flightHours
Indicates the number of hours an entity has spent in flight or operating in the air.
-
E.
isGroundedIn
Indicates that something is based on, supported by, or justified through a particular source, foundation, or set of principles.
- 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_69ca842cbddc819099d71ecec48cf9e5 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd5080f55c8190bd5ca0dc0a4ea989 |
completed | April 1, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69cc7a6abb8c81908c7a2f4ee92cc949 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:43 p.m.