Triple
T17253911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MARCOM |
E418830
|
entity |
| Predicate | acronym |
P43
|
FINISHED |
| Object | MARCOM |
E418830
|
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: MARCOM | Statement: [MARCOM, acronym, MARCOM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MARCOM Context triple: [MARCOM, acronym, MARCOM]
-
A.
MARCOM
chosen
MARCOM is NATO’s principal maritime headquarters responsible for the command and control of Allied naval forces.
-
B.
Veromandui
The Veromandui were an ancient Belgic tribe of northern Gaul, known from Roman sources for inhabiting the region around modern Vermand in present-day France.
-
C.
Aspar
Aspar was a powerful 5th-century Alan general and kingmaker in the Eastern Roman Empire who dominated imperial politics from behind the throne.
-
D.
Martinus
Martinus is the given first name of Dutch sprinter and later police officer Tinus Osendarp, a notable athlete of the 1930s.
-
E.
Vartan
Vartan is a surname most notably associated with French-American actor Michael Vartan.
- 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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e6b2b1c8190b446ce648ecaad80 |
completed | April 19, 2026, 1:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170fd7f7c81908f417fa758e861a2 |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.