Triple
T15561045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Mattingly |
E370997
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Mattingly |
E369889
|
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: Mattingly | Statement: [Thomas Mattingly, familyName, Mattingly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mattingly Context triple: [Thomas Mattingly, familyName, Mattingly]
-
A.
Mattingly
chosen
Mattingly is a surname most notably associated with figures such as astronaut Ken Mattingly and baseball player Don Mattingly.
-
B.
Harold Mattingly
Harold Mattingly was a British historian and numismatist best known for his influential work on Roman coinage and inscriptions.
-
C.
Bob Mattey
Bob Mattey was a renowned special effects artist best known for designing and building mechanical creatures for films, including the iconic shark in "Jaws."
-
D.
David Mattingly
David Mattingly is a British archaeologist and historian known for his influential research on the Roman Empire, particularly in North Africa and frontier studies.
-
E.
Milt
Milt is a masculine given name, typically used as a shortened form of Milton.
- 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_69d85cc6cf40819091f4a5facee1ebe6 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ddb4c0c81909b3f4c75c91f7f3f |
completed | April 16, 2026, 2:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff456821988190971539b683f6c656 |
completed | May 9, 2026, 2:32 p.m. |
Created at: April 10, 2026, 4:09 a.m.