Triple
T7920014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parachute Jump tower |
E183921
|
entity |
| Predicate | yearDecommissioned |
P14100
|
FINISHED |
| Object | 1964 |
—
|
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: 1964 | Statement: [Parachute Jump tower, yearDecommissioned, 1964]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearDecommissioned Context triple: [Parachute Jump tower, yearDecommissioned, 1964]
-
A.
decommissionedDate
chosen
Indicates the date on which an entity was formally taken out of service or retired from active use.
-
B.
decommissioningEndDate
Indicates the date on which a decommissioning process or status for something is completed or officially ends.
-
C.
decommissionedWith
Indicates that an entity was taken out of service or retired in conjunction with, or as part of the same process as, another specified entity.
-
D.
decommissionedReason
Indicates the reason or cause for which an entity, typically an asset or system, was taken out of service or formally retired.
-
E.
decommissioningStartDate
Indicates the date on which the process of taking an asset or system out of active service is initiated.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a9173548190a04889726f7b251f |
completed | March 31, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:05 p.m.