Triple
T10542869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shaffer Smith |
E248739
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mad |
E587299
|
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: Mad | Statement: [Shaffer Smith, notableWork, Mad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mad Context triple: [Shaffer Smith, notableWork, Mad]
-
A.
Mad
chosen
"Mad" is an R&B ballad by American singer Ne-Yo, known for its emotional lyrics about conflict and reconciliation in a relationship.
-
B.
Deranged
Deranged is a 1974 Canadian-American horror film loosely based on the crimes of Ed Gein, noted for its grim, realistic portrayal of a necrophilic killer.
-
C.
Paranoimia
Paranoimia is a 1986 electronic pop track by the avant-garde group Art of Noise, best known for its innovative production and collaboration with the computer-generated character Max Headroom.
-
D.
Mal
Mal is a common shortened form of the given name Malcolm.
-
E.
Mot
Mot is the Phoenician god of death and the underworld, associated with sterility, drought, and the cyclical struggle against life-giving deities.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5190f46d08190a92b1191881ffb92 |
completed | April 7, 2026, 2:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9342e6cf48190b0ca53ff2a4e0214 |
completed | April 10, 2026, 5:32 p.m. |
Created at: April 6, 2026, 12:32 p.m.