Triple
T34673584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BHP Billiton |
E890440
|
entity |
| Predicate | historicalCompetitor |
P22384
|
FINISHED |
| Object | De Beers |
—
|
NE NERFINISHED |
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: De Beers | Statement: [BHP Billiton, historicalCompetitor, De Beers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalCompetitor Context triple: [BHP Billiton, historicalCompetitor, De Beers]
-
A.
hasCompetitionHistory
Indicates that an entity has a recorded history of participation in competitions or competitive events.
-
B.
historicalStrength
Indicates the relative power, influence, or effectiveness an entity possessed during a specified past period.
-
C.
hasHistoricRivalry
chosen
Indicates a long-standing, often competitive or adversarial relationship between two entities, typically rooted in significant past conflicts or repeated opposition.
-
D.
historicalTopCompetition
Indicates that an entity has participated in or been associated with the highest-level or most prestigious competition within a historical context.
-
E.
historicalComparison
Indicates a relationship where one entity is evaluated or contrasted with another in terms of their characteristics, significance, or context across different historical periods.
- 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_69f349d9c59481908b36baa0be093aea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a007899cadc8190a04edd503eaf6514 |
completed | May 10, 2026, 12:22 p.m. |
| PD | Predicate disambiguation | batch_6a0078493e088190b0c5047cbe75d304 |
completed | May 10, 2026, 12:21 p.m. |
Created at: May 1, 2026, 2:05 a.m.