Triple
T5669322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elliot Roberts |
E124935
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Elliot Roberts |
E124935
|
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: Elliot Roberts | Statement: [Elliot Roberts, name, Elliot Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elliot Roberts Context triple: [Elliot Roberts, name, Elliot Roberts]
-
A.
Elliot Roberts
chosen
Elliot Roberts was a prominent American music manager and record executive best known for guiding the careers of artists like Neil Young and Joni Mitchell.
-
B.
Elliot Scott
Elliot Scott was a British film art director and production designer known for his work on major films including "Indiana Jones and the Temple of Doom."
-
C.
Elliot Davis
Elliot Davis is a cinematographer known for his work on the film "Out of Sight."
-
D.
Elliot Randall
Elliot Randall is an American session guitarist best known for his work with Steely Dan and numerous rock and pop artists.
-
E.
Elliot
Elliot is the friendly, invisible green dragon who befriends and protects a young orphan boy in Disney’s family film "Pete’s Dragon."
- 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_69c00828906881908966f270b8f130cf |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0234891d48190bf662f38ef84d4f3 |
completed | March 22, 2026, 5:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04dafb6b081909c5bf1527f185819 |
completed | March 22, 2026, 8:14 p.m. |
Created at: March 22, 2026, 3:43 p.m.