Triple
T13104498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalie Morales |
E310808
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Language Lessons |
E1022991
|
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: Language Lessons | Statement: [Natalie Morales, directed, Language Lessons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Language Lessons Context triple: [Natalie Morales, directed, Language Lessons]
-
A.
Language Lessons
chosen
Language Lessons is a 2021 intimate, dialogue-driven drama film co-written by and starring Natalie Morales, who also directed it.
-
B.
Lessons
Lessons is a 2022 novel by Ian McEwan that follows a man's life across decades of personal and historical upheaval, exploring memory, trauma, and the passage of time.
-
C.
Lesson
Lesson is a French surname most notably borne by René Primevère Lesson, a 19th-century French surgeon, naturalist, and explorer.
-
D.
Zattoo
Zattoo is an internet-based live TV and streaming platform that allows users to watch television channels online across various devices.
-
E.
TeachText
TeachText was a simple text-editing application bundled with early versions of the classic Mac OS, primarily used for reading documentation and creating basic text files.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98153255c8190b6ab64ac0c4716f8 |
completed | April 10, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6ead8f3a881909a32afc268e3b385 |
completed | May 3, 2026, 6:27 a.m. |
Created at: April 9, 2026, 9:05 p.m.