Triple
T8775731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deep Water |
E208576
|
entity |
| Predicate | album |
P1995
|
FINISHED |
| Object | Seal |
E35256
|
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: Seal | Statement: [Deep Water, album, Seal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seal Context triple: [Deep Water, album, Seal]
-
A.
Seal
chosen
Seal is a British singer-songwriter known for his soulful voice and hit songs such as "Kiss from a Rose."
-
B.
Seal
Seal is a village in the Sevenoaks district of Kent, England, known for its historic parish church and traditional rural character.
-
C.
Seals
Seals is the nickname of the historic San Francisco Seals baseball team, a prominent minor league club that played in the Pacific Coast League.
-
D.
Bond
Bond is a survivor perk in Dead by Daylight that allows players to see the auras of nearby teammates, enhancing coordination and support.
-
E.
Bond
Bond is a common English surname historically associated with occupational or status-based origins and borne by numerous notable figures across politics, arts, and popular culture.
- 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_69ca835fbee88190bf625939bac48d7f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f30428881909de72c08972224f0 |
completed | March 31, 2026, 11:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d05bd623b88190aeecaa70f92e5c3c |
completed | April 4, 2026, 12:31 a.m. |
Created at: March 30, 2026, 6:41 p.m.