Triple
T12060226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hector the Bulldog |
E287146
|
entity |
| Predicate | oftenSeenAs |
P18297
|
FINISHED |
| Object | bodyguard |
—
|
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: bodyguard | Statement: [Hector the Bulldog, oftenSeenAs, bodyguard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenSeenAs Context triple: [Hector the Bulldog, oftenSeenAs, bodyguard]
-
A.
oftenUsedAsNameFor
Indicates that something frequently serves as a name or designation for another entity.
-
B.
oftenExpressedAs
Indicates that one thing is frequently represented, stated, or manifested in the form of another.
-
C.
oftenDepictedAs
chosen
Indicates that one entity is frequently represented or portrayed in the form, appearance, or symbolism of another entity.
-
D.
knownAsOneOf
Indicates that an entity is recognized or referred to as one member of a specified set of alternative names, labels, or identities.
-
E.
oftenBroadcastAs
Indicates that something is frequently transmitted or aired through a broadcast medium under a particular form, title, or version.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:48 p.m.