Triple
T16943237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | May Morning celebrations |
E410999
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | May Day |
E38228
|
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: May Day | Statement: [May Morning celebrations, relatedTo, May Day]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: May Day Context triple: [May Morning celebrations, relatedTo, May Day]
-
A.
May Day
chosen
May Day is an international labor holiday celebrated on May 1st, marked by demonstrations, marches, and events advocating workers’ rights and social justice.
-
B.
May Day
May Day is a formidable and iconic Bond villain henchwoman, portrayed by Grace Jones in the 1985 James Bond film "A View to a Kill."
-
C.
May Day
"May Day" is a 1920 short story by F. Scott Fitzgerald that portrays post–World War I disillusionment and class conflict in New York City.
-
D.
Mayday
Mayday is a prominent electronic music track by German producer and DJ Alexander Ridha, better known as Boys Noize.
-
E.
Mayday
Mayday is a 2021 surreal war-fantasy film that blends dreamlike visuals with a feminist reimagining of conflict and survival.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfafc8448190a25be8ada84eff9c |
completed | April 18, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfea3bc88190acaa013169d607c5 |
completed | May 10, 2026, 6:35 p.m. |
Created at: April 10, 2026, 5:31 a.m.