Triple
T15821667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragon |
E383626
|
entity |
| Predicate | member |
P10
|
FINISHED |
| Object | Mark Williams |
E1043794
|
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: Mark Williams | Statement: [Dragon, member, Mark Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Williams Context triple: [Dragon, member, Mark Williams]
-
A.
Mark Williams
Mark Williams is a Christian songwriter known for co-writing the contemporary worship song "Lord I Need You."
-
B.
Mark Williams
Mark Williams is a film and television producer best known for co-creating the series "Ozark" and producing action-thriller films starring Ben Affleck and Liam Neeson.
-
C.
Mark Williams
Mark Williams is a British actor best known for playing Arthur Weasley in the Harry Potter film series.
-
D.
Mark Williams
Mark Williams is a Welsh professional snooker player and multiple-time world champion renowned for his calm demeanor and exceptional long-potting ability.
-
E.
Mark Williams
chosen
Mark Williams is a musician best known as a member of the American music production and songwriting duo Ojivolta.
- 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_69d86da2858c819090cc8481e7207b6e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0c4a887d881908f74a1fcba390727 |
completed | April 16, 2026, 11:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff99999c2c8190b1838aed40e12061 |
completed | May 9, 2026, 8:31 p.m. |
Created at: April 10, 2026, 4:49 a.m.