Triple
T11005631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Lexington (CV-2) |
E260109
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Lady Lex |
E260109
|
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: Lady Lex | Statement: [USS Lexington (CV-2), nickname, Lady Lex]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Lex Context triple: [USS Lexington (CV-2), nickname, Lady Lex]
-
A.
Lady Lex
chosen
Lady Lex is the famous nickname of USS Lexington (CV-2), a pioneering U.S. Navy aircraft carrier that served prominently in the early Pacific campaigns of World War II.
-
B.
Lexa
Lexa is a feminine given name, commonly used as a short form of Alexandra.
-
C.
Lady L
Lady L is a 1965 romantic comedy film, based on a Romain Gary novel, known for its satirical take on love and class in early 20th-century Europe and starring Sophia Loren, Paul Newman, and David Niven.
-
D.
Lady Mi
Lady Mi was a noblewoman of the late Eastern Han dynasty, best known as one of the wives of warlord Liu Bei and for her tragic death during his escape from enemy forces.
-
E.
Lea
Lea is a given name used across various cultures, often as a variant of Leah or Léa.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797562de4819097a0e136180d283a |
completed | April 9, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3454cb6008190b24b128d507f2cf4 |
completed | April 18, 2026, 8:48 a.m. |
Created at: April 8, 2026, 9:25 p.m.