Triple
T49434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curse of the Bambino |
E971
|
entity |
| Predicate | notableBreakingEvent |
P259
|
FINISHED |
| Object | 2004 ALCS comeback vs New York Yankees |
—
|
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 ALCS comeback vs New York Yankees | Statement: [Curse of the Bambino, notableBreakingEvent, 2004 ALCS comeback vs New York Yankees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBreakingEvent Context triple: [Curse of the Bambino, notableBreakingEvent, 2004 ALCS comeback vs New York Yankees]
-
A.
significantEvent
chosen
Indicates that an event involving the entities is of notable importance or impact within a given context.
-
B.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
C.
notableEventDate
Indicates the date on which a notable or significant event associated with the subject occurred.
-
D.
notableOutcome
Indicates that an action, event, or entity leads to or is associated with a significant, noteworthy result or consequence.
-
E.
notableHolder
Indicates that a person or entity is a distinguished or prominent holder of a particular position, title, or role.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c1a5c14819088748317a3f262c8 |
completed | Feb. 28, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69a24abfa7bc8190932c137a823efcb6 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.