Triple
T30989162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curtiss F9C Sparrowhawk |
E789618
|
entity |
| Predicate | airshipBase |
P171114
|
FINISHED |
| Object | USS Akron (ZRS-4) |
—
|
NE NERFINISHED |
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: USS Akron (ZRS-4) | Statement: [Curtiss F9C Sparrowhawk, airshipBase, USS Akron (ZRS-4)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airshipBase Context triple: [Curtiss F9C Sparrowhawk, airshipBase, USS Akron (ZRS-4)]
-
A.
airshipClass
Indicates the classification or type category to which an airship belongs.
-
B.
airshipTypeUsedWith
Indicates that a particular type of airship is typically or appropriately used in conjunction with a given object, system, or context.
-
C.
airshipNumber
Indicates the identifying number assigned to a specific airship within a set or system.
-
D.
airshipBoss
Indicates that one entity serves as the primary controlling or commanding figure over an airship-related context or scenario involving another entity.
-
E.
aircraftBase
Indicates that a particular location serves as the primary base or home station for an aircraft or group of aircraft.
- 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_69f224c550b081909ddfceb0c3d03bdd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f698ad83a08190a6834056ccc3e3a4 |
completed | May 3, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
| PDg | Predicate description generation | batch_69f697e92e2c8190bed50d5ba0981b64 |
completed | May 3, 2026, 12:33 a.m. |
Created at: April 29, 2026, 8:56 p.m.