Triple
T17075837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomas Masiulis |
E414345
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Tomas |
E143480
|
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: Tomas | Statement: [Tomas Masiulis, givenName, Tomas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tomas Context triple: [Tomas Masiulis, givenName, Tomas]
-
A.
Tomas
chosen
Tomas is a masculine given name commonly used in various European and Latin American countries, often equivalent to "Thomas" in English.
-
B.
Tomaz
Tomaz is the protagonist of the story "Amulet," around whom the central plot and character development revolve.
-
C.
Tomáš
Tomáš is a masculine given name commonly used in Czech and Slovak cultures, equivalent to Thomas in English.
-
D.
Tomasino
Tomasino is the colloquial term used to refer to students of the University of Santo Tomas in the Philippines.
-
E.
Tomasso
Tomasso is a character from the Marx Brothers’ classic comedy film "A Night at the Opera," contributing to the movie’s farcical and musical antics.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc47808819088a4ca039689b213 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012edfda588190aff6c6d4c8d64ddd |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:34 a.m.