Triple
T21999344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian Navy special forces |
E543283
|
entity |
| Predicate | hasUnit |
P35
|
FINISHED |
| Object | MARCOS |
—
|
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: MARCOS | Statement: [Indian Navy special forces, hasUnit, MARCOS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MARCOS Context triple: [Indian Navy special forces, hasUnit, MARCOS]
-
A.
MARCOS
chosen
MARCOS is the Indian Navy’s elite maritime special operations force, trained for high-risk missions such as amphibious warfare, counterterrorism, and covert reconnaissance.
-
B.
MARCO
MARCO is a prominent contemporary art museum in Monterrey, Mexico, known for its modern architecture and rotating exhibitions of national and international artists.
-
C.
Markos
Markos is a given name, commonly used in Greek and other cultures, that corresponds to the variant form "Marcos."
-
D.
Marcio
Marcio is a masculine given name commonly used in Portuguese- and Spanish-speaking countries, derived from the Latin name Marcius.
-
E.
Mateus
Mateus is a Portuguese surname commonly borne by individuals such as Rui Mateus.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12768c0088190b0c8d5cd9b7bf710 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:19 p.m.