Triple
T34097208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulletproof |
E874462
|
entity |
| Predicate | featuresRealityTVShow |
P3279
|
FINISHED |
| Object | 16 and Pregnant |
E55529
|
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: 16 and Pregnant | Statement: [Bulletproof, featuresRealityTVShow, 16 and Pregnant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresRealityTVShow Context triple: [Bulletproof, featuresRealityTVShow, 16 and Pregnant]
-
A.
networkOfRealityShow
Indicates that a particular reality show is broadcast or produced by a specific television network.
-
B.
hasRealityTVElement
Indicates that something includes characteristics, themes, or stylistic features commonly associated with reality television.
-
C.
featuresReturnOf
Indicates that something (such as a work, event, or product) includes or highlights the comeback or reappearance of a person, character, element, or feature.
-
D.
televisionShow
chosen
Indicates that one entity is a television show associated with, or featured in relation to, another entity.
-
E.
featuresCast
Indicates that a creative work includes a particular person or group as part of its cast.
- F. None of above.
Provenance (4 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_69f349a735208190a1dbfb1c2a121059 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a02fc3890a881908b69b0f2d7cc1ce1 |
completed | May 12, 2026, 10:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a372116acd88190b628ca6718960ec3 |
completed | June 20, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_6a02fb98438c8190938896c00216b9ec |
completed | May 12, 2026, 10:06 a.m. |
Created at: May 1, 2026, 1:53 a.m.