Triple
T18282518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seraphim |
E437896
|
entity |
| Predicate | groupedWith |
P2830
|
FINISHED |
| Object | Thrones |
—
|
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: Thrones | Statement: [Seraphim, groupedWith, Thrones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thrones Context triple: [Seraphim, groupedWith, Thrones]
-
A.
Thrones
chosen
Thrones is a later sequence of poems within Ezra Pound's long modernist work "The Cantos," reflecting his complex political, economic, and historical ideas.
-
B.
Iron Throne
The Iron Throne is the iconic, jagged metal seat of power in the Game of Thrones universe, symbolizing ultimate authority over the Seven Kingdoms of Westeros.
-
C.
Place du Trône
Place du Trône is the former name of a historic Parisian square now known as Place de la Nation, a major public space in eastern Paris.
-
D.
Place du Trône
Place du Trône is a prominent square in Brussels situated near the Royal Palace, known for its role as a key junction in the city's royal and administrative district.
-
E.
The Throne
The Throne is the hip hop duo of Jay-Z and Kanye West, best known for their collaborative album "Watch the Throne."
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50057c5c881909fcda72f4a98c8c3 |
completed | April 19, 2026, 4:18 p.m. |
Created at: April 10, 2026, 10:35 a.m.