Triple
T5128496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Draco Malfoy |
E115637
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Tom Felton |
E118209
|
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: Tom Felton | Statement: [Draco Malfoy, portrayedBy, Tom Felton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Felton Context triple: [Draco Malfoy, portrayedBy, Tom Felton]
-
A.
Tom Felton
chosen
Tom Felton is an English actor best known for playing Draco Malfoy in the Harry Potter film series.
-
B.
Rupert Grint
Rupert Grint is an English actor best known for playing Ron Weasley in the Harry Potter film series.
-
C.
Nicholas Brendon
Nicholas Brendon is an American actor best known for playing Xander Harris on the television series "Buffy the Vampire Slayer."
-
D.
Daniel Radcliffe
Daniel Radcliffe is an English actor best known for playing the title role in the Harry Potter film series.
-
E.
Liam Aiken
Liam Aiken is an American actor known for his roles as a child and teen in films such as "A Series of Unfortunate Events," "Good Boy!" and "Stepmom."
- 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_69bd444426bc819099ccd23f141e22aa |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7825facc8190b2a6c17216290b5c |
completed | March 20, 2026, 4:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bec4beb7b48190a2f4e41a13fdd5f3 |
completed | March 21, 2026, 4:18 p.m. |
Created at: March 20, 2026, 1:42 p.m.