Triple
T3730266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Invincibles (Arsenal 2003–04) |
E79043
|
entity |
| Predicate | leaguePoints |
P7114
|
FINISHED |
| Object | 90 |
—
|
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: 90 | Statement: [The Invincibles (Arsenal 2003–04), leaguePoints, 90]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leaguePoints Context triple: [The Invincibles (Arsenal 2003–04), leaguePoints, 90]
-
A.
careerPoints
Indicates the total number of points an individual has accumulated over the course of their entire career in a given activity or domain.
-
B.
leagueLeader
Indicates that the subject entity is currently ranked first or holds the top position within a specified league or competitive grouping.
-
C.
winnerPoints
chosen
Indicates the number of points earned by the winning participant or entity in a competition or event.
-
D.
teamLevel
Indicates the hierarchical rank or tier at which a team operates within an organization, competition, or structure.
-
E.
leagueContext
Indicates the broader league or competition setting within which the relationship or action takes place.
- 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_69ad8b0e4650819090ad7cef094285e8 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb1bb5408190990ea4dfbdab5c68 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc04746588190b0dc535638f23546 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.