Triple
T16402451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Essex |
E398333
|
entity |
| Predicate | hullNumber |
P3152
|
FINISHED |
| Object | CV-9 |
E398331
|
NE 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: CV-9 | Statement: [USS Essex, hullNumber, CV-9]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CV-9 Context triple: [USS Essex, hullNumber, CV-9]
-
A.
CV-9
chosen
CV-9 is the hull number of USS Essex, a World War II-era Essex-class aircraft carrier of the United States Navy that played a major role in Pacific Theater operations.
-
B.
CV-990
CV-990 is a narrow-body jet airliner developed by Convair in the early 1960s, known for being one of the fastest commercial passenger aircraft ever built.
-
C.
CV-39
CV-39 is the hull number of USS Lake Champlain, an Essex-class aircraft carrier that served in the United States Navy during and after World War II.
-
D.
C-9
C-9 is a mountain railway line of Madrid’s Cercanías commuter rail network that connects the city with the Sierra de Guadarrama, including the Puerto de Navacerrada and Cotos areas.
-
E.
CV-4
CV-4 is the hull number of USS Ranger, the first U.S. Navy aircraft carrier designed and built from the keel up as a carrier.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e327d0652081908f42f78b156f3ae7 |
completed | April 18, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f439d048190bf779cb263b7c7a7 |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:09 a.m.