Triple
T28612512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HTC Dream |
E724199
|
entity |
| Predicate | carrierVariant |
P164831
|
FINISHED |
| Object | T-Mobile US |
—
|
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: T-Mobile US | Statement: [HTC Dream, carrierVariant, T-Mobile US]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carrierVariant Context triple: [HTC Dream, carrierVariant, T-Mobile US]
-
A.
specificCarrierVariant
chosen
Indicates that one entity is a particular, more narrowly defined version or subtype of a broader carrier entity.
-
B.
mobileVariant
Indicates that one entity is a mobile-specific version or adaptation of another entity.
-
C.
carrierExclusiveVariant
Indicates that a variant is available only through a specific carrier and not through others.
-
D.
carrierType
Indicates the type or category of carrier involved in the relationship or action (e.g., the kind of entity that carries or transports something).
-
E.
carrierOf
Indicates that one entity serves as the medium, vehicle, or host that contains, transports, or conveys another entity.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 4:30 a.m.