Triple
T36303494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Michelinie |
E893883
|
entity |
| Predicate | wroteForTitle |
P185118
|
FINISHED |
| Object | Iron Man |
—
|
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: Iron Man | Statement: [David Michelinie, wroteForTitle, Iron Man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wroteForTitle Context triple: [David Michelinie, wroteForTitle, Iron Man]
-
A.
workWrittenFor
Indicates that a creative work was specifically composed, produced, or created for a particular person, group, event, purpose, or medium.
-
B.
wroteIn
Indicates that an entity authored or composed something using a particular language, medium, or writing system.
-
C.
wroteSubtitle
Indicates that one entity is the author or creator of the subtitle text associated with another entity, such as a film, video, or media work.
-
D.
writtenAgainst
Indicates that a written work (such as a document, article, or statement) is composed in opposition to, or as a critique or complaint about, a particular target.
-
E.
wroteForFormat
Indicates that an entity authored or created content specifically for a particular format or medium.
- F. None of above. chosen
Provenance (4 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_69f76e4c1b248190b10667d0213537fe |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7bb1d6b70819091227bd011734d19 |
completed | May 3, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
| PDg | Predicate description generation | batch_69f7ba6c27e081908868a2b50d1d603c |
completed | May 3, 2026, 9:13 p.m. |
Created at: May 3, 2026, 4:09 p.m.