Triple
T23938234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Robinson |
E602700
|
entity |
| Predicate | duoNickname |
P67622
|
FINISHED |
| Object | Twin Towers |
—
|
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: Twin Towers | Statement: [David Robinson, duoNickname, Twin Towers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: duoNickname Context triple: [David Robinson, duoNickname, Twin Towers]
-
A.
nicknameOfChampionDuo
chosen
Indicates that a given nickname refers to or is used for a specific champion duo.
-
B.
hasAffectionateNicknameFor
Indicates that one entity uses or assigns a fond, affectionate, or endearing nickname to another entity.
-
C.
hasNicknames
Indicates that an entity is known or referred to by one or more alternative informal names.
-
D.
unofficialNickname
Indicates that one entity is informally or colloquially known by a non-official nickname represented by the other entity.
-
E.
dedicatedToOrNicknameOf
Indicates that one entity is either the dedicatee of something (e.g., a work, object, or honor) or serves as an alternative name or nickname for 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cfa267b88190a1e7d599f22441e2 |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:07 p.m.