Triple
T15011332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Datis |
E377842
|
entity |
| Predicate | campaignEndedWith |
P116348
|
FINISHED |
| Object | Persian defeat at the Battle of Marathon |
—
|
LITERAL 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: Persian defeat at the Battle of Marathon | Statement: [Datis, campaignEndedWith, Persian defeat at the Battle of Marathon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignEndedWith Context triple: [Datis, campaignEndedWith, Persian defeat at the Battle of Marathon]
-
A.
campaignEnded
Indicates that a previously active campaign has concluded and is no longer ongoing.
-
B.
sponsorshipEndedWith
Indicates that a previously existing sponsorship relationship between entities has come to an end.
-
C.
sponsorshipEnded
Indicates that a previously existing sponsorship relationship between entities has been terminated or has come to an end.
-
D.
alsoEnded
Indicates that one event or state concluded in addition to another already mentioned event or state.
-
E.
sponsorEnded
Indicates that a sponsorship relationship between entities has been terminated or has come to an end.
- F. None of above. chosen
Provenance (4 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7613cec8190ac25e3f68c5d0edf |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69deb1a88d588190996afa8e5b32b552 |
completed | April 14, 2026, 9:29 p.m. |
Created at: April 10, 2026, 2:55 a.m.