Triple
T21877519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hard Attack |
E540186
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Ivory |
—
|
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: Ivory | Statement: [Hard Attack, hasTrack, Ivory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ivory Context triple: [Hard Attack, hasTrack, Ivory]
-
A.
Ivory
chosen
Ivory is a surname most notably associated with James Ivory, the acclaimed American film director, producer, and screenwriter known for his work with Merchant Ivory Productions.
-
B.
Persia White
Persia White is an American actress and musician best known for her role as Lynn Searcy on the television sitcom "Girlfriends."
-
C.
Albine
Albine is a central character in Émile Zola’s novel *La Faute de l’Abbé Mouret*, symbolizing natural innocence and forbidden love in contrast to the priest’s religious devotion.
-
D.
Beryl
Beryl is a given name that can be used for people of any gender, historically more common as a female name in English-speaking countries.
-
E.
Parangolés
Parangolés are a series of wearable, participatory artworks created by Brazilian artist Hélio Oiticica that merge painting, sculpture, and performance to explore movement, color, and viewer interaction.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c479a98081908ce333853fdd4348 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f33c012c819096d0f7b2ffdc7a2f |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 7:02 p.m.