Triple
T9996970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shakira as Gazelle |
E197224
|
entity |
| Predicate | marketedAs |
P1395
|
FINISHED |
| Object | Gazelle |
E253264
|
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: Gazelle | Statement: [Shakira as Gazelle, marketedAs, Gazelle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gazelle Context triple: [Shakira as Gazelle, marketedAs, Gazelle]
-
A.
Gazelle
chosen
Gazelle is a lethal, acrobatic assassin from the Kingsman film series, recognizable for her bladed prosthetic legs and role as Richmond Valentine’s chief enforcer.
-
B.
Gazelle
The Gazelle is a light, fast, and highly maneuverable French-designed military helicopter widely used for reconnaissance, light attack, and training missions.
-
C.
GAZelle
GAZelle is a popular line of light commercial vehicles produced by the Russian manufacturer GAZ Group, widely used for cargo and passenger transport.
-
D.
Gazella
Gazella is a genus of small, swift antelopes commonly known as gazelles, native to arid and semi-arid regions of Africa and Asia.
-
E.
Thomson's gazelle
Thomson's gazelle is a small, swift African antelope known for its distinctive black side stripe and agility on the open savannas of East Africa.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc8aa1a881909879a694496f11a5 |
completed | April 2, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2583bd6948190b15a97187e81d958 |
completed | April 5, 2026, 12:40 p.m. |
Created at: March 30, 2026, 8:51 p.m.