Triple
T1748051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gravity |
E38378
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Matt Kowalski |
E82138
|
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: Matt Kowalski | Statement: [Gravity, mainCharacter, Matt Kowalski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Kowalski Context triple: [Gravity, mainCharacter, Matt Kowalski]
-
A.
Matt Kowalski
chosen
Matt Kowalski is a veteran NASA astronaut and spacewalker featured as a central character in the science fiction film "Gravity."
-
B.
Greg Grissom
Greg Grissom is a sports executive who serves as the president of the NFL’s Houston Texans franchise.
-
C.
Kowalski
Kowalski is a surname of Polish origin commonly used in Poland and among Polish diaspora communities.
-
D.
Kai Dugan
Kai Dugan is the son of American actress Jennifer Connelly, known primarily for his connection to his famous mother.
-
E.
Hank Mann
Hank Mann was a prolific silent film comedian and character actor, best known as one of the original Keystone Cops and for his numerous supporting roles in early Hollywood comedies.
- 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_69a8862b01a48190ab47209063af82d9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa63ecda0c819091f81942a5bde31d |
completed | March 6, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada0e058948190939e936af8f0e221 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 4, 2026, 7:31 p.m.