Triple
T9466648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MIT Linguistics Section |
E228287
|
entity |
| Predicate | notableFaculty |
P141
|
FINISHED |
| Object | Donca Steriade |
E174231
|
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: Donca Steriade | Statement: [MIT Linguistics Section, notableFaculty, Donca Steriade]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donca Steriade Context triple: [MIT Linguistics Section, notableFaculty, Donca Steriade]
-
A.
Donca Steriade
chosen
Donca Steriade is a prominent linguist and phonologist known for influential work on segmental phonology, syllable structure, and the theory of lexical and positional neutralization.
-
B.
Mircea Dinescu
Mircea Dinescu is a Romanian poet, dissident, and public intellectual known for his outspoken opposition to the Ceaușescu regime and his prominent role in the 1989 Romanian Revolution.
-
C.
Gheorghe Avramescu
Gheorghe Avramescu was a Romanian general during World War II who played a significant role on the Eastern Front and later in Romania’s switch to the Allied side.
-
D.
Ioan Negulescu
Ioan Negulescu, better known as Jean Negulesco, was a Romanian-born American film director and screenwriter noted for his work in Hollywood during the 1940s and 1950s, including films like "How to Marry a Millionaire."
-
E.
Dumitru Erhan
Dumitru Erhan is a computer scientist and machine learning researcher known for influential work in deep learning and neural networks.
- 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_69ca846fee388190a6ec273fd644b88b |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7fdc08f08190ad17de08d2c2eca2 |
completed | April 1, 2026, 8:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d122ba3d948190a3fa947cd3cad63b |
completed | April 4, 2026, 2:39 p.m. |
Created at: March 30, 2026, 7:53 p.m.