Triple
T36456214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | JT11D-20 |
E898157
|
entity |
| Predicate | hasSpecialSystem |
P197966
|
FINISHED |
| Object | fuel as heat sink for engine and airframe |
—
|
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: fuel as heat sink for engine and airframe | Statement: [JT11D-20, hasSpecialSystem, fuel as heat sink for engine and airframe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialSystem Context triple: [JT11D-20, hasSpecialSystem, fuel as heat sink for engine and airframe]
-
A.
hasSpecial
Indicates that an entity possesses or is associated with a distinctive or exceptional attribute, status, or feature compared to others.
-
B.
hasSpecialUse
Indicates that an entity is used for a particular, non-general or exceptional purpose within a specific context.
-
C.
hasSpecialUnit
Indicates that an entity possesses or is associated with a distinct, designated unit that has a special role, function, or status.
-
D.
hasSpecialBody
Indicates that an entity possesses a distinctive or non-standard physical form or body type compared to typical instances in its category.
-
E.
hasSpecials
Indicates that an entity offers or is associated with special deals, promotions, or limited-time offers.
- 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_69f76e57f08481908593bd0bc34581c8 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69febce5877c8190a5e000ef5331ec88 |
completed | May 9, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_69febad1cd588190abc7686bcb39a371 |
completed | May 9, 2026, 4:40 a.m. |
| PDg | Predicate description generation | batch_69febce420b081908e1c052751a22b1f |
completed | May 9, 2026, 4:49 a.m. |
Created at: May 3, 2026, 4:10 p.m.