Triple
T33347637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pool of Death (2015 Rugby World Cup) |
E853842
|
entity |
| Predicate | featuredTierTwoTeam |
P203577
|
FINISHED |
| Object | Fiji national rugby union team |
E819643
|
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: Fiji national rugby union team | Statement: [Pool of Death (2015 Rugby World Cup), featuredTierTwoTeam, Fiji national rugby union team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredTierTwoTeam Context triple: [Pool of Death (2015 Rugby World Cup), featuredTierTwoTeam, Fiji national rugby union team]
-
A.
featuredTeam
Indicates that a particular team is highlighted or given special prominence in a given context or presentation.
-
B.
featuresTeams
Indicates that something prominently presents or includes specific teams as a central element or focus.
-
C.
team2
Indicates that the second team involved in a competitive or collaborative context is associated with a given entity or event.
-
D.
stateTeam2
Indicates that a second team is associated with, represents, or belongs to a particular state or region.
-
E.
featuresTeamLevel
Indicates that a feature is available or applicable at the team (rather than individual or organization) level.
- F. None of above. chosen
Provenance (5 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_69f3496a1a588190bad9cbe9221144e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a01a819644c819094c58d083d525da0 |
completed | May 11, 2026, 9:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a358141d44c819088b114dca7185961 |
completed | June 19, 2026, 5:49 p.m. |
| PD | Predicate disambiguation | batch_6a01a5dfd628819083c032d8cfd2e726 |
completed | May 11, 2026, 9:48 a.m. |
| PDg | Predicate description generation | batch_6a01a818bb708190ba6dbf883349df39 |
completed | May 11, 2026, 9:57 a.m. |
Created at: May 1, 2026, 1:34 a.m.