Triple
T26954274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transco Tower, Houston |
E678854
|
entity |
| Predicate | laterRenamedFor |
P16968
|
FINISHED |
| Object | Williams Companies |
—
|
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: Williams Companies | Statement: [Transco Tower, Houston, laterRenamedFor, Williams Companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterRenamedFor Context triple: [Transco Tower, Houston, laterRenamedFor, Williams Companies]
-
A.
wereRenamedAs
Indicates that one entity previously had a different name and was subsequently given or adopted the other entity as its new name.
-
B.
laterNamed
chosen
Indicates that an entity was given a new name at a later time, linking its original identity to its subsequent name.
-
C.
wasRenamedIn
Indicates that an entity changed its name to a different one at or during a specific time or event.
-
D.
renamedDueTo
Indicates that one entity was renamed as a consequence of another specified cause, event, or condition.
-
E.
oftenRenamedAs
Indicates that an entity is frequently given a different name or title, reflecting common renaming or rebranding over time or across contexts.
- 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_69eeeb4e75f08190b14fc91ca4a91488 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c475c58c8190a883554231e88c88 |
completed | May 3, 2026, 9:56 p.m. |
Created at: April 27, 2026, 6:26 a.m.