Triple
T30580080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World Trade Center Site Memorial Competition |
E778358
|
entity |
| Predicate | winningDesignAnnounced |
P149477
|
FINISHED |
| Object | 2004-01-14 |
—
|
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: 2004-01-14 | Statement: [World Trade Center Site Memorial Competition, winningDesignAnnounced, 2004-01-14]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winningDesignAnnounced Context triple: [World Trade Center Site Memorial Competition, winningDesignAnnounced, 2004-01-14]
-
A.
designCompetitionWonBy
Indicates that a particular design competition was won by a specified participant or entity.
-
B.
winnerAnnouncedIn
chosen
Indicates that the winner of a competition, contest, or award is formally declared or made public within a specific event, ceremony, or context.
-
C.
designCompetitionWinYear
Indicates the year in which an entity won a particular design competition.
-
D.
uniqueAndArtisticPictureWinner
Indicates that the subject has won an award or recognition specifically for creating a picture judged to be both unique and artistic.
-
E.
awardResult
Indicates the outcome or status of an award process, linking an award event to its final decision or result.
- F. None of above.
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_69f224a04b248190b0ca443ec86207b8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6894176d0819096fe66b9baab66f1 |
completed | May 2, 2026, 11:31 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:23 p.m.