Triple
T9839467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shark |
E239184
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Henry Simmons |
E275930
|
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: Henry Simmons | Statement: [Shark, starring, Henry Simmons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Simmons Context triple: [Shark, starring, Henry Simmons]
-
A.
Henry Simmons
chosen
Henry Simmons is an American actor best known for his roles on the television series NYPD Blue and Marvel's Agents of S.H.I.E.L.D.
-
B.
Jake Simmonds
Jake Simmonds is a character from the Doctor Who universe who appears in the two-part story involving the rise of the Cybermen in a parallel Earth.
-
C.
Dane Witherspoon
Dane Witherspoon was an American actor best known for his roles in daytime soap operas during the 1980s.
-
D.
Anthony Tolliver
Anthony Tolliver is an American professional basketball player known for his long NBA career as a versatile, three-point-shooting forward and respected locker-room veteran.
-
E.
Jonathan Kimble Simmons
Jonathan Kimble Simmons is an American actor known for his versatile character roles in film and television, including his Oscar-winning performance in "Whiplash."
- 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_69ca84e3f0c48190ada72a65ebd50efd |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb34b045481908f89abd576aab497 |
completed | April 2, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5d145ac8190ad10a4328216ef54 |
completed | April 5, 2026, 3:24 a.m. |
Created at: March 30, 2026, 8:33 p.m.