Triple
T22256299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Ellis |
E550102
|
entity |
| Predicate | stageName |
P7872
|
FINISHED |
| Object | Flood |
—
|
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: Flood | Statement: [Mark Ellis, stageName, Flood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Flood Context triple: [Mark Ellis, stageName, Flood]
-
A.
Flood
Flood is a common English surname of Germanic origin, often associated with families from regions prone to flooding or near bodies of water.
-
B.
Flood
Flood is a landmark 1963 abstract expressionist painting by Helen Frankenthaler, celebrated for its lyrical color field technique and innovative use of thinned paint poured directly onto unprimed canvas.
-
C.
Flood
chosen
Flood is a renowned British record producer and audio engineer known for his work with influential rock and alternative artists such as U2, Depeche Mode, and Nine Inch Nails.
-
D.
Flood
"Flood" is a science fiction novel by Stephen Baxter that explores a near-future Earth devastated by a mysterious, relentless rise in global sea levels.
-
E.
Flood
The Flood is a parasitic alien species in the Halo universe that infects and assimilates other lifeforms, serving as one of the series’ primary antagonistic forces.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c314308190a5eea84e1750158a |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.