Triple
T102794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021 MLS Supporters' Shield |
E2075
|
entity |
| Predicate | secondaryCriterion |
P136
|
FINISHED |
| Object | goal difference if points are equal |
—
|
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: goal difference if points are equal | Statement: [2021 MLS Supporters' Shield, secondaryCriterion, goal difference if points are equal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryCriterion Context triple: [2021 MLS Supporters' Shield, secondaryCriterion, goal difference if points are equal]
-
A.
secondaryGoal
Indicates that something serves as a subordinate or supporting objective in addition to a primary goal.
-
B.
secondaryFunction
Indicates that an entity has an additional, supporting role or purpose beyond its primary function.
-
C.
secondaryDomain
Indicates that one domain functions as a secondary or auxiliary domain in relation to a primary domain.
-
D.
selectionCriteria
chosen
Indicates the conditions or rules used to choose certain entities from a larger set.
-
E.
secondLetter
Indicates that one entity is the second letter (in sequence or position) of another entity, typically a string or word.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a2563a6ff48190bec582fb2f99b7af |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.